© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 69779
    Prev
    Next
    INDEX
    Explanations

    references to hand gestures and their significance in communication

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

    gestures and signs

    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
    :+:
    -0.45
    angliski
    -0.43
    RegressionTest
    -0.43
    httphttps
    -0.41
    XtraReports
    -0.41
     surla
    -0.40
    Попис
    -0.38
     Eintritt
    -0.36
     kaynağından
    -0.36
     onBind
    -0.36
    POSITIVE LOGITS
     gestures
    1.45
     gesture
    1.41
     gest
    1.37
     Gest
    1.30
     hand
    1.25
     GEST
    1.14
     Gesture
    1.14
     sign
    1.13
    gest
    1.11
     signal
    1.11
    Activations Density 0.121%

    No Known Activations