© 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 - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 10679
    Prev
    Next
    INDEX
    Explanations

    physical interactions and gestures involving hands

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

    "Hand" near body parts or objects

    np_acts-logits-general · gemini-2.0-flash

    actions involving hands and body

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    başı
    -0.32
    canActivate
    -0.32
    eds
    -0.31
     jsPsych
    -0.30
     cro
    -0.30
    geräte
    -0.29
     presup
    -0.29
    ext
    -0.28
    oa̍t
    -0.28
     mac
    -0.28
    POSITIVE LOGITS
     defaultstate
    0.66
    Portail
    0.59
     Infórmanos
    0.59
    queryInterface
    0.58
    
    0.54
    Bakgrunnsstoff
    0.53
    aarrggbb
    0.52
    ValueStyle
    0.51
     PeEnEo
    0.51
    
    0.50
    Activations Density 0.391%

    No Known Activations