© 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
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 105063
    Prev
    Next
    INDEX
    Explanations

    topics and discussions related to race, racism, and racial identity

    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
    RegressionTest
    -0.78
    RenderAtEndOf
    -0.77
    ChildScrollView
    -0.75
    enumii
    -0.73
    SequentialGroup
    -0.71
    Rüyada
    -0.69
    +#+#
    -0.69
    <unused79>
    -0.67
    <unused14>
    -0.67
    <pad>
    -0.67
    POSITIVE LOGITS
     gender
    0.46
     identity
    0.39
     issues
    0.39
     classification
    0.38
     matters
    0.37
     differences
    0.33
     identities
    0.32
     parties
    0.32
     status
    0.32
     concerns
    0.32
    Activations Density 0.066%

    No Known Activations