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-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 15822
    Prev
    Next
    INDEX
    Explanations

    monosyllabic abbreviations or shorthand notations in technical or scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
    клопе
    -0.66
    ScopeManager
    -0.65
    IMPORTED
    -0.65
    PREFERRED
    -0.65
    AddHtmlAttribute
    -0.58
    ölkerung
    -0.57
    มาะ
    -0.56
    Население
    -0.56
    preter
    -0.56
    ation
    -0.56
    POSITIVE LOGITS
    Beijinhos
    0.62
    cartão
    0.54
    Katso
    0.51
     CS
    0.50
     PhD
    0.48
    kwij
    0.48
     digitais
    0.48
    COUVER
    0.47
     NW
    0.47
     MD
    0.47
    Activations Density 1.170%

    No Known Activations