© 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. 9-GEMMASCOPE-RES-131K
    11. 37334
    Prev
    Next
    INDEX
    Explanations

    instances of the word "find."

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

    finding facts or states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Schlegel
    -0.71
    ologous
    -0.65
     statusCode
    -0.63
     Chappell
    -0.62
    oulou
    -0.60
    ViewFeatures
    -0.60
    orithmic
    -0.60
    AutoresizingMask
    -0.60
     newUser
    -0.60
    AppRoutingModule
    -0.60
    POSITIVE LOGITS
    find
    1.27
     find
    1.24
    Find
    1.21
     Find
    1.16
     FIND
    1.12
    FIND
    1.08
     finds
    0.95
    finds
    0.86
     finder
    0.83
    Finding
    0.82
    Activations Density 0.032%

    No Known Activations