© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 110415
    Prev
    Next
    INDEX
    Explanations

    programming language constructs related to class definitions and method implementations

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

    returning responses

    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
    UseVisualStyle
    -0.37
     ElementRef
    -0.37
     consulté
    -0.35
    DllImport
    -0.34
    FormsModule
    -0.32
     Вікі
    -0.32
    Requested
    -0.31
    selected
    -0.31
     Espíritu
    -0.31
     mouseClicked
    -0.31
    POSITIVE LOGITS
     response
    0.75
     Response
    0.68
     respond
    0.64
     Resp
    0.63
     Respond
    0.61
     responds
    0.61
     responses
    0.60
     respuesta
    0.59
     Responses
    0.59
     responders
    0.58
    Activations Density 0.014%

    No Known Activations