© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 105253
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     Olsson
    -0.36
     Erickson
    -0.36
     Mühle
    -0.36
     Atenas
    -0.35
    jamientos
    -0.35
     Andersson
    -0.35
     Lindberg
    -0.34
     Steuer
    -0.33
     Rauch
    -0.33
     Persson
    -0.32
    POSITIVE LOGITS
     BoxFit
    7.38
     MainAxisSize
    1.19
     TextAlign
    1.09
     FetchType
    1.02
     AssemblyVersion
    0.99
     BorderRadius
    0.97
    ChildScrollView
    0.97
     TextInputType
    0.96
     BoxDecoration
    0.94
    AxisAlignment
    0.93
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.