© 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
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 12739
    Prev
    Next
    INDEX
    Explanations

    instances of characters interacting and turning their gaze or attention towards one another

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

    This neuron detects moments when a character turns their head or body to face another person.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    Lähteet
    -0.40
     oprot
    -0.38
     trữ
    -0.36
     Noviembre
    -0.33
     McDonough
    -0.32
     Wicidata
    -0.32
    viembre
    -0.31
     purpoſe
    -0.30
    getMenuInflater
    -0.30
    깥
    -0.30
    POSITIVE LOGITS
     turning
    1.52
     turn
    1.46
     Turning
    1.44
    Turning
    1.38
     turned
    1.38
    turning
    1.38
     Turn
    1.37
    turn
    1.36
    Turn
    1.31
     Turned
    1.30
    Activations Density 0.108%

    No Known Activations