© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 13-GEMMASCOPE-RES-16K
    11. 10243
    Prev
    Next
    INDEX
    Explanations

    references to women and children's issues or topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abestanden
    -0.60
    LookAnd
    -0.49
    rungsseite
    -0.45
     transférez
    -0.42
    AutoModerator
    -0.41
    ználat
    -0.41
    gamento
    -0.41
     firebaseConfig
    -0.39
    Tembelea
    -0.39
     Esatti
    -0.39
    POSITIVE LOGITS
     womens
    0.63
    richTextPanel
    0.60
     Womens
    0.57
     Adult
    0.53
    Women
    0.52
    womens
    0.49
    Adult
    0.49
    adult
    0.48
     femininos
    0.47
     Women
    0.46
    Activations Density 0.468%

    No Known Activations