© 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-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 3912
    Prev
    Next
    INDEX
    Explanations

    significant changes and their implications in societal structures

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    major negative consequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    HasForeignKey
    -0.92
    AsUp
    -0.88
    TypedDataSet
    -0.80
    ThroughAttribute
    -0.78
    ViewImports
    -0.75
    DockStyle
    -0.73
     doInBackground
    -0.73
     HttpNotFound
    -0.72
    ResumeLayout
    -0.72
    MigrationBuilder
    -0.72
    POSITIVE LOGITS
     consequences
    2.56
     effects
    2.19
     Consequences
    2.14
     consequence
    1.97
     effect
    1.96
     Effects
    1.96
    Consequences
    1.95
     conséquences
    1.93
     impact
    1.93
     impacts
    1.91
    Activations Density 0.383%

    No Known Activations