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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 38032
    Prev
    Next
    INDEX
    Explanations

    technical specifications and measurements related to equipment or materials

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

    pipe fittings and valves

    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
    PCell
    -0.35
     Unters
    -0.33
    MatIconModule
    -0.33
     MotionEvent
    -0.33
    openqa
    -0.32
    ướng
    -0.31
    optString
    -0.31
    ピック
    -0.31
    rrggbb
    -0.30
     Marion
    -0.29
    POSITIVE LOGITS
     flanges
    0.71
     Fittings
    0.70
    Personendaten
    0.68
     fittings
    0.67
     pipe
    0.65
     Valves
    0.61
    MigrationBuilder
    0.61
     Pipe
    0.61
    Pressure
    0.59
     valves
    0.59
    Activations Density 0.045%

    No Known Activations