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. 2031
    Prev
    Next
    INDEX
    Explanations

    specific numerical data and numerical references in various contexts

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

    technical terms and multilingual links

    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
    fjspx
    -0.50
     autorytatywna
    -0.45
     Administrativna
    -0.45
     Wicidata
    -0.44
    стон
    -0.44
    SharedCtor
    -0.39
    WebElementEntity
    -0.39
    reathable
    -0.38
    thasone
    -0.38
     Combustion
    -0.37
    POSITIVE LOGITS
    Cyfeiriadau
    0.57
     وتسجيلات
    0.50
    Nuorodos
    0.47
    .*")]
    0.47
    Décès
    0.46
     يتيمه
    0.46
     lenker
    0.44
    Hentet
    0.43
     BoxFit
    0.43
     transfieras
    0.42
    Activations Density 0.072%

    No Known Activations