© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 42487
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
    Not in Any Lists

    No Comments

    Negative Logits
    ✥
    -0.39
     injustices
    -0.37
    pd
    -0.35
    div
    -0.33
     bez
    -0.32
    hept
    -0.32
    pidou
    -0.31
    unrecognized
    -0.30
    pav
    -0.29
    fvar
    -0.29
    POSITIVE LOGITS
    tangentMode
    0.88
    WebVitals
    0.81
    AndroidJUnit
    0.79
     nahilalakip
    0.78
     transfieras
    0.75
     tartalomajánló
    0.66
    PreferredItem
    0.65
    ſelves
    0.64
     invokingState
    0.63
     MainAxisSize
    0.62
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.