© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 41-GEMMASCOPE-RES-16K
    11. 13674
    Prev
    Next
    INDEX
    Explanations

    instances of sitting or resting in various contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     resourceCulture
    -0.55
     незавершена
    -0.52
     يتيمه
    -0.52
    WillAppear
    -0.48
     Normdatei
    -0.47
     snippetHide
    -0.46
    Sucesor
    -0.46
    windowFixed
    -0.46
     strijd
    -0.45
     BorderRadius
    -0.43
    POSITIVE LOGITS
     idle
    0.64
     quietly
    0.62
     motionless
    0.59
     comfortably
    0.57
     patiently
    0.57
     idly
    0.56
     cross
    0.56
     tight
    0.55
     crossed
    0.53
     bolt
    0.52
    Activations Density 0.178%

    No Known Activations