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. 14043
    Prev
    Next
    INDEX
    Explanations

    function declarations and calls in programming code

    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
     initComponents
    -0.81
    তথ্যসূত্র
    -0.72
     snippetHide
    -0.71
     Roskov
    -0.71
    DockStyle
    -0.71
    InputBorder
    -0.70
    Portail
    -0.68
    ReusableCell
    -0.63
    VersionUID
    -0.62
     >=",
    -0.60
    POSITIVE LOGITS
     man
    0.61
    RenderAtEndOf
    0.50
     Man
    0.43
     believe
    0.42
     بلو
    0.41
    PMailer
    0.41
     trực
    0.41
     learned
    0.40
     human
    0.39
    VarChar
    0.38
    Activations Density 0.052%

    No Known Activations