© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 36-GEMMASCOPE-RES-16K
    11. 13421
    Prev
    Next
    INDEX
    Explanations

    topics related to gender representation and diversity in media and technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/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.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     statt
    -0.75
     anstatt
    -0.71
     вместо
    -0.68
     zamiast
    -0.62
    じゃなくて
    -0.60
    الحياه
    -0.60
     Biôgrafia
    -0.60
    ではなく
    -0.59
     Statt
    -0.59
     rather
    -0.56
    POSITIVE LOGITS
     counterparts
    0.78
     pourtant
    0.67
     counterpart
    0.65
     does
    0.63
     did
    0.56
    เคย
    0.54
     eût
    0.53
     sekal
    0.49
     similarly
    0.48
    does
    0.47
    Activations Density 0.574%

    No Known Activations