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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 77035
    Prev
    Next
    INDEX
    Explanations

    key technical terms and specifications related to products or devices

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     גל
    -0.33
    FLICT
    -0.30
    GLO
    -0.29
     ilişk
    -0.29
    quely
    -0.28
    KommentareTeilen
    -0.28
    deferred
    -0.28
    퇴
    -0.28
     чтения
    -0.28
    brin
    -0.28
    POSITIVE LOGITS
     Vape
    0.67
     vape
    0.65
    vape
    0.63
     flavours
    0.61
    省市镇
    0.60
    Autoritní
    0.58
    aarrggbb
    0.56
    يكب
    0.55
    $_['
    0.54
    arbox
    0.54
    Activations Density 0.000%

    No Known Activations