© 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. 9111
    Prev
    Next
    INDEX
    Explanations

    references to layout positioning and margin values in UI design

    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
    </thead>
    -0.45
    supra
    -0.37
    ConstraintMaker
    -0.36
    
    -0.35
    OPSIS
    -0.35
    scribers
    -0.34
     supr
    -0.33
     cappuccio
    -0.33
    SizeMode
    -0.33
    invokeLater
    -0.33
    POSITIVE LOGITS
     bottom
    3.61
     Bottom
    3.11
    bottom
    3.00
    Bottom
    2.97
     BOTTOM
    2.80
     bottoms
    2.61
    BOTTOM
    2.52
    底
    2.28
    botto
    2.14
    底部
    2.05
    Activations Density 0.689%

    No Known Activations