© 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. 22-GEMMASCOPE-RES-16K
    11. 3627
    Prev
    Next
    INDEX
    Explanations

    references to social roles and gender dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    她們
    -0.40
    RTLU
    -0.40
    glGen
    -0.40
    优化
    -0.39
    聋
    -0.38
     myr
    -0.38
    Mira
    -0.38
     licencia
    -0.38
    TextUtils
    -0.37
     mutagenesis
    -0.37
    POSITIVE LOGITS
    恥ず
    0.63
     embarrassed
    0.60
     embarrassing
    0.57
     embarrassment
    0.57
     manly
    0.54
     embarrass
    0.53
     Admit
    0.53
     ashamed
    0.52
     admitting
    0.51
     ModelExpression
    0.51
    Activations Density 0.265%

    No Known Activations