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. 16-GEMMASCOPE-RES-16K
    6. 12096
    Prev
    Next
    INDEX
    Explanations

    references to data and statistics related to societal issues and demographics

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

    Follows a symbol or abbreviation

    np_acts-logits-general · gemini-2.0-flash

    extreme intensity or scale

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     esternos
    -0.69
    writeFieldEnd
    -0.67
    DoubleQuotes
    -0.64
    ngdoc
    -0.58
    Tasty
    -0.55
    ServletException
    -0.55
    LEncoder
    -0.54
     مشين
    -0.53
     ModelExpression
    -0.53
    databind
    -0.52
    POSITIVE LOGITS
     extreme
    0.91
    extreme
    0.83
     extrême
    0.79
    Extreme
    0.76
     Extreme
    0.73
     ultra
    0.73
     estrema
    0.70
     tiny
    0.67
     extremo
    0.66
     extremely
    0.64
    Activations Density 0.657%

    No Known Activations