Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 64874
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and imports in code

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

    singers, request, user input

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    Autoritní
    -0.66
    jsxFileName
    -0.55
     Verſ
    -0.52
     Administrativna
    -0.50
     skb
    -0.48
     ſeinen
    -0.48
    newArrayList
    -0.47
    timewa
    -0.47
    AddTagHelper
    -0.47
    Cyfarwyddwr
    -0.46
    POSITIVE LOGITS
    QMetaType
    0.42
    TProtocol
    0.41
    GTCX
    0.40
    dotto
    0.30
     isInitialized
    0.29
     geldig
    0.29
    的关系
    0.28
     согласи
    0.27
    onRequest
    0.27
    anças
    0.27
    Activations Density 0.003%

    No Known Activations