© 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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 58188
    Prev
    Next
    INDEX
    Explanations

    occurrences of parentheses in the text

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

    acronym endings

    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
    دانشنامهٔ
    -0.65
    reactstrap
    -0.55
    inSlope
    -0.54
    TryDecodeAsNil
    -0.54
    msgTypes
    -0.53
    AnchorStyles
    -0.50
     препратки
    -0.49
    Subviews
    -0.47
    __*/
    -0.46
     مشين
    -0.46
    POSITIVE LOGITS
    انجليز
    0.37
     incluidos
    0.36
     Chwiliwch
    0.34
    loat
    0.34
     nutrición
    0.33
     Officially
    0.33
     zdrav
    0.33
     incluidas
    0.32
    ecido
    0.32
    ArrowToggle
    0.31
    Activations Density 0.023%

    No Known Activations