Manifold curvature and intrinsic dimension predict layerwise SAE width exponents and asymptotic floors across Gemma models, with cross-model transfer of the geometric regression, establishing a transferable geometric law instead of a universal scaling law.
Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 1
dataset 1
method 1
citation-polarity summary
years
2026 7verdicts
UNVERDICTED 7representative citing papers
LOCA identifies an average of six minimal interpretable changes in intermediate representations that causally induce refusal on otherwise successful jailbreaks for Gemma and Llama models.
LLMs show a grounding gap with humans on abstract concepts, with property-generation correlations at most r=0.37 versus human-to-human r>0.9, though larger models align better on explicit rating tasks and internal SAE features capture some grounding dimensions.
Activation steering is cast as constrained optimization that minimizes collateral damage by weighting perturbations according to the empirical second-moment matrix of activations instead of assuming isotropy.
Blocking a fixed set of latent features during fine-tuning reduces emergent misalignment by up to 95% across six domains with no loss in target task performance.
ConceptTracer supplies an interactive interface and saliency/selectivity metrics to locate concept-responsive neurons in neural representations, shown on TabPFN.
Qwen-Scope provides open-source sparse autoencoders for Qwen models that function as practical interfaces for steering, evaluating, data workflows, and optimizing large language models.
citing papers explorer
-
The Geometric Wall: Manifold Structure Predicts Layerwise Sparse Autoencoder Scaling Laws
Manifold curvature and intrinsic dimension predict layerwise SAE width exponents and asymptotic floors across Gemma models, with cross-model transfer of the geometric regression, establishing a transferable geometric law instead of a universal scaling law.
-
Minimal, Local, Causal Explanations for Jailbreak Success in Large Language Models
LOCA identifies an average of six minimal interpretable changes in intermediate representations that causally induce refusal on otherwise successful jailbreaks for Gemma and Llama models.
-
The Grounding Gap: How LLMs Anchor the Meaning of Abstract Concepts Differently from Humans
LLMs show a grounding gap with humans on abstract concepts, with property-generation correlations at most r=0.37 versus human-to-human r>0.9, though larger models align better on explicit rating tasks and internal SAE features capture some grounding dimensions.
-
Minimizing Collateral Damage in Activation Steering
Activation steering is cast as constrained optimization that minimizes collateral damage by weighting perturbations according to the empirical second-moment matrix of activations instead of assuming isotropy.
-
BLOCK-EM: Preventing Emergent Misalignment via Latent Blocking
Blocking a fixed set of latent features during fine-tuning reduces emergent misalignment by up to 95% across six domains with no loss in target task performance.
-
ConceptTracer: Interactive Analysis of Concept Saliency and Selectivity in Neural Representations
ConceptTracer supplies an interactive interface and saliency/selectivity metrics to locate concept-responsive neurons in neural representations, shown on TabPFN.
-
Qwen-Scope: Turning Sparse Features into Development Tools for Large Language Models
Qwen-Scope provides open-source sparse autoencoders for Qwen models that function as practical interfaces for steering, evaluating, data workflows, and optimizing large language models.