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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 15152
    Prev
    Next
    INDEX
    Explanations

    code structure elements and delimiters such as semicolons and parentheses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    paramref
    -0.56
    '][]
    -0.50
    rrggbb
    -0.50
    
    -0.49
    }")]
    -0.49
     DbSet
    -0.48
    unjungi
    -0.48
    .="
    -0.48
    });*/
    -0.47
    ']->
    -0.47
    POSITIVE LOGITS
     import
    0.78
    import
    0.77
    {
    
    0.72
     виправивши
    0.67
     {
    
    0.65
    Geplaatst
    0.63
    public
    0.62
     Meksiku
    0.55
     Bact
    0.54
    InjectAttribute
    0.53
    Activations Density 0.019%

    No Known Activations