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

    Neuronpedia

    APICircuit 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. 20-GEMMASCOPE-RES-16K
    6. 10255
    Prev
    Next
    INDEX
    Explanations

    code and programming constructs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Start of code: var, function, class, def

    np_acts-logits-general · gemini-2.0-flash

    programming code keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    consulté
    -0.68
    ++
    
    -0.68
    >\<^
    -0.63
     Commencez
    -0.60
     IndexPath
    -0.59
    BagConstraints
    -0.58
    ulario
    -0.58
    ,‎
    -0.56
    NOPQRST
    -0.55
    ️⃣
    -0.55
    POSITIVE LOGITS
    import
    0.93
     import
    0.83
    var
    0.68
    function
    0.66
    class
    0.66
     function
    0.66
    let
    0.65
     #
    0.65
    def
    0.64
    #!/
    0.63
    Activations Density 1.016%

    No Known Activations