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. 1124
    Prev
    Next
    INDEX
    Explanations

    names of individuals and institutions related to significant contributions or research in various fields

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

    notable individuals related to creative fields or film

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

    Maharashtra and its cities

    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
    Autoritní
    -0.77
     autorytatywna
    -0.76
    Xna
    -0.76
    Personendaten
    -0.71
    MigrationBuilder
    -0.68
    Hentet
    -0.68
    Hochspringen
    -0.68
     وتسجيلات
    -0.63
     Spisak
    -0.63
    MENAFN
    -0.62
    POSITIVE LOGITS
     Marathi
    0.89
     Pune
    0.80
     Maharashtra
    0.78
    Maharashtra
    0.70
    Pune
    0.69
     Patil
    0.66
     pune
    0.64
     NCP
    0.60
    gaon
    0.54
     Mumbai
    0.53
    Activations Density 0.037%

    No Known Activations