© 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 - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 15755
    Prev
    Next
    INDEX
    Explanations

    expressions related to societal issues and inequalities, particularly concerning gender and race

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

    women

    np_acts-logits-general · gemini-2.0-flash

    gender and relationships

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    бенок
    -0.52
    Child
    -0.49
    CHILD
    -0.46
     Child
    -0.44
    Parent
    -0.44
    child
    -0.43
     شوهر
    -0.42
     PARENT
    -0.42
     familial
    -0.42
    Family
    -0.41
    POSITIVE LOGITS
     women
    1.14
     woman
    1.07
     girls
    0.98
     guys
    0.91
     ladies
    0.88
     lady
    0.84
     men
    0.81
     boys
    0.81
     vrouwen
    0.79
     wanita
    0.79
    Activations Density 0.320%

    No Known Activations