© 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. 37-GEMMASCOPE-RES-16K
    11. 9075
    Prev
    Next
    INDEX
    Explanations

    features related to automotive design and technology

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    tagHelperRunner
    -0.59
     flywheel
    -0.55
    ValueStyle
    -0.47
    +#+
    -0.47
    
    -0.46
     jScrollPane
    -0.46
     synapse
    -0.45
    PerformLayout
    -0.45
     Spine
    -0.45
     Syna
    -0.43
    POSITIVE LOGITS
     fog
    0.68
     Fog
    0.65
    Fog
    0.59
    fog
    0.57
     parking
    0.54
     niebla
    0.50
    Parking
    0.49
     wiper
    0.48
    存于互联网档案馆
    0.48
     signal
    0.47
    Activations Density 0.333%

    No Known Activations