Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 13721
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and notation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     comparison
    -0.57
    ')):
    -0.57
    '])->
    -0.56
     שוליים
    -0.53
    )();
    -0.52
    égard
    -0.51
    )');
    -0.51
     compare
    -0.50
    ))^{
    -0.50
    ")));
    
    -0.50
    POSITIVE LOGITS
     +
    1.88
     plus
    1.65
    +
    1.58
     $+$
    1.51
    +
    1.44
     плюс
    1.43
     PLUS
    1.40
     $+
    1.39
     + 
    1.34
    }+
    1.33
    Activations Density 1.815%

    No Known Activations