© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 2827
    Prev
    Next
    INDEX
    Explanations

    technical terms and identifiers related to programming and system operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    principalColumn
    -0.90
     فريبيس
    -0.82
    thâu
    -0.74
    GEBURTSDATUM
    -0.72
     Chwiliwch
    -0.71
     oprot
    -0.69
     ویکی‌پدی
    -0.68
     Normdatei
    -0.65
    oa̍t
    -0.65
     Мексичка
    -0.62
    POSITIVE LOGITS
    addPreferredGap
    0.37
    synchronized
    0.35
    -------------</
    0.34
    化
    0.31
    dyž
    0.31
     Covington
    0.31
    findOneAndUpdate
    0.30
     Kleine
    0.29
    程序
    0.29
    warnai
    0.28
    Activations Density 0.496%

    No Known Activations