SemanticScuttle - klotz.me

klotz: interpretability* + gemma scope* + analysis* + visualization* + deepmind* + autoencoder*

0 bookmark(s) - Sort by: Date ↓ / Title / - Bookmarks from other users for this tag

1. Gemma Scope: helping the safety community shed light on the inner workings of language models

   DeepMind's Gemma Scope provides researchers with tools to better understand how Gemma 2 language models work through a collection of sparse autoencoders. This helps in understanding the inner workings of these models and addressing concerns like hallucinations and potential manipulation.

   2024-11-14 Tags: llm, interpretability, gemma scope, autoencoder, deepmind, visualization, xai, analysis by klotz

Top of the page

First / Previous / Next / Last / Page 1 of 0