© 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 EvalsExportsAPI 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. 103306
    Prev
    Next
    INDEX
    Explanations

    references to judicial nominations and the political implications surrounding them

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    Not in Any Lists

    No Comments

    Negative Logits
    enapa
    -0.41
     ModelRenderer
    -0.40
    Containing
    -0.37
     ordinary
    -0.35
    MigrationBuilder
    -0.35
    PreExecute
    -0.35
     électron
    -0.34
     Strut
    -0.34
    NewUrlParser
    -0.33
    atiker
    -0.33
    POSITIVE LOGITS
     replacement
    0.69
     replacements
    0.68
    MLLoader
    0.66
     Replacement
    0.63
    replacement
    0.58
     replace
    0.58
    Replacement
    0.58
     reempla
    0.56
     remplacement
    0.56
     repla
    0.50
    Activations Density 0.097%

    No Known Activations