Skip to content
#

gemmascope

Star

Here is 1 public repository matching this topic...

nulone / sae-consciousness-steering-pitfalls

Star 1

Reproducible case study of pitfalls in contrastive SAE discovery and steering for "consciousness" features (GemmaScope SAEs, Gemma 3 4B/12B): reconstruction confound, delta-steering fix, matched controls, and false-positive scaling law vs dataset size.

gemma sae sparse-autoencoder contrastive-learning mechanistic-interpretability feature-steering neuronpedia null-result gemmascope delta-steering
  • Updated Feb 26, 2026
  • Python

Improve this page

Add a description, image, and links to the gemmascope topic page so that developers can more easily learn about it.

Curate this topic

Add this topic to your repo

To associate your repository with the gemmascope topic, visit your repo's landing page and select "manage topics."

Learn more