© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 66515
    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
    skap
    -0.40
    fal
    -0.38
     classifier
    -0.36
    lock
    -0.35
    Lock
    -0.34
     slave
    -0.34
     grecque
    -0.34
    akat
    -0.34
    Sat
    -0.33
     tones
    -0.33
    POSITIVE LOGITS
     通販
    3.16
    Tembelea
    0.71
    Derbyniad
    0.71
    脚注の使い方
    0.71
    ChildScrollView
    0.68
    Билгалдахарш
    0.66
     виправивши
    0.66
     disambiguazione
    0.65
     snippetHide
    0.63
     informée
    0.63
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.