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 - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 1094
    Prev
    Next
    INDEX
    Explanations

    statements or phrases highlighting statistical data and comparisons

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

    verbs indicating positive contributions or additions

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

    conditions or states

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    WithTag
    -0.42
    StoreMessageInfo
    -0.39
    חים
    -0.37
    Сто
    -0.36
    oretical
    -0.36
    zyny
    -0.36
     peix
    -0.36
    bashrc
    -0.35
     Gier
    -0.35
    svd
    -0.34
    POSITIVE LOGITS
    IntoConstraints
    0.89
     autorytatywna
    0.84
     whoſe
    0.83
    Revenir
    0.80
     prices
    0.79
    overall
    0.77
     whofe
    0.77
    الدراسه
    0.75
     rates
    0.74
     Roskov
    0.73
    Activations Density 0.354%

    No Known Activations