© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 37176
    Prev
    Next
    INDEX
    Explanations

    references to aesthetically appealing or attractive attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    attractive women and sexuality

    np_acts-logits-general · gemini-2.5-flash-lite

    text referencing sexualized images or displays of women (nudity, erotic photos/calendars, body parts, and related promotional content).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
     שוליים
    -0.46
     autorytatywna
    -0.45
    Transcripción
    -0.41
     indicador
    -0.40
     resourceCulture
    -0.40
     Mumford
    -0.40
     pathway
    -0.40
    InjectAttribute
    -0.39
    tagHelperRunner
    -0.39
    ArgumentParser
    -0.38
    POSITIVE LOGITS
     Playboy
    0.59
     bikini
    0.56
     Bikini
    0.53
     bikinis
    0.53
     seksi
    0.50
     desnuda
    0.49
    👙
    0.46
     sexy
    0.46
     boobs
    0.45
     Sexy
    0.45
    Activations Density 0.041%

    No Known Activations