© 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 EvalsExportsAPI 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. 14985
    Prev
    Next
    INDEX
    Explanations

    instances of reaching or extending hands, often in a context of interaction or introduction

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

    extending or reaching out

    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
    SharedCtor
    -0.47
    WriteTagHelper
    -0.37
    httphttps
    -0.33
    CodeAttribute
    -0.31
    Tembelea
    -0.31
     समीक्षाएं
    -0.30
    IGENCE
    -0.30
     кое
    -0.30
    WireFormatLite
    -0.30
    cookieParser
    -0.30
    POSITIVE LOGITS
     outstretched
    1.57
     stretched
    1.28
     extend
    1.26
     extending
    1.26
     extended
    1.21
     Extending
    1.21
     extends
    1.18
     Extend
    1.17
     протя
    1.15
    伸
    1.14
    Activations Density 0.038%

    No Known Activations