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

    Neuronpedia

    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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 74811
    Prev
    Next
    INDEX
    Explanations

    references to testing frameworks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    Жен
    -1.86
     Жен
    -0.81
    Women
    -0.63
     women
    -0.60
     Women
    -0.59
    women
    -0.57
    Woman
    -0.54
     woman
    -0.52
     Frauen
    -0.50
     Woman
    -0.50
    POSITIVE LOGITS
     ExecuteAsync
    5.53
    protoimpl
    1.63
     CreateTagHelper
    1.33
    LITERAL
    1.25
    RegressionTest
    1.13
    MigrationBuilder
    1.05
    новништво
    1.05
     disambiguazione
    1.00
    rungsseite
    0.98
    __(/*!
    0.96
    Activations Density 0.000%

    No Known Activations