© 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. 31-GEMMASCOPE-RES-131K
    6. 91309
    Prev
    Next
    INDEX
    Explanations

    language related to legal objections and courtroom proceedings

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

    objections and birth

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    expandindo
    -0.68
    RectangleBorder
    -0.59
    DockStyle
    -0.58
     ExecuteAsync
    -0.57
    RegressionTest
    -0.55
    BufferException
    -0.54
    XMLSchema
    -0.54
     getRule
    -0.52
     Tela
    -0.52
     للاسماء
    -0.52
    POSITIVE LOGITS
     thereto
    1.02
     to
    0.75
     hereto
    0.63
     vistazo
    0.52
    到的
    0.47
     tomu
    0.45
    ToObject
    0.45
     '\\;'
    0.45
    于
    0.44
     Comprometido
    0.43
    Activations Density 0.115%

    No Known Activations