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. 30617
    Prev
    Next
    INDEX
    Explanations

    specific numerical references or identifiers related to legal documents or case numbers

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

    past numbers

    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
    الدراسه
    -0.36
     '\\;'
    -0.32
     propOrder
    -0.32
     跳转至
    -0.31
    ":[{
    -0.31
     تضيفلها
    -0.31
     snippetHide
    -0.30
     tartalomajánló
    -0.30
     jspb
    -0.30
    FieldBuilder
    -0.29
    POSITIVE LOGITS
     ২০১
    0.54
     Vergangenheit
    0.54
     passada
    0.54
     maternidade
    0.53
    loga
    0.52
     ainfi
    0.52
     movimentos
    0.51
     թվ
    0.50
     Infór
    0.50
     dahulu
    0.50
    Activations Density 0.054%

    No Known Activations