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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 39428
    Prev
    Next
    INDEX
    Explanations

    instances of the word "look" in various forms, indicating an interest in searching or examining information

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

    investigating, exploring, looking into

    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
     disambiguazione
    -0.52
    AddTagHelper
    -0.52
     sumpay
    -0.49
     MainAxisSize
    -0.49
     estekak
    -0.48
    DockStyle
    -0.45
    AccessorTable
    -0.44
    ۜ
    -0.44
    UnknownFields
    -0.43
    ็จ
    -0.42
    POSITIVE LOGITS
     investigate
    0.79
     investigating
    0.78
     investigated
    0.74
     Investigate
    0.73
     exploring
    0.73
     explore
    0.67
     investigar
    0.65
     Investigating
    0.65
     investigation
    0.65
     investigates
    0.65
    Activations Density 0.013%

    No Known Activations