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. 16-GEMMASCOPE-RES-65K
    6. 53221
    Prev
    Next
    INDEX
    Explanations

    formatting symbols and characters, particularly those used in HTML or programming contexts

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

    table structure/layout

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ulco
    -0.68
     Montagu
    -0.66
    tami
    -0.61
    badan
    -0.61
    mybatisplus
    -0.60
     Sass
    -0.56
    gatsby
    -0.56
     Genova
    -0.56
     Walters
    -0.56
    keley
    -0.56
    POSITIVE LOGITS
    cline
    1.75
     متعلقه
    0.82
     مشين
    0.77
    multirow
    0.74
     autorytatywna
    0.73
     manne
    0.71
     nahilalakip
    0.69
     surla
    0.68
     rowspan
    0.67
     colspan
    0.67
    Activations Density 0.002%

    No Known Activations