© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 55052
    Prev
    Next
    INDEX
    Explanations

    sexually charged terms and expressions related to attraction and sexuality

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

    sexual, erotic, suggestive

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     للمعارف
    -0.71
    CloseOperation
    -0.60
    tagHelperRunner
    -0.59
    :"-"`
    -0.58
     resourceCulture
    -0.58
    хьтан
    -0.57
    TestingModule
    -0.57
     disambiguazione
    -0.52
    IsContent
    -0.52
    Portail
    -0.52
    POSITIVE LOGITS
     sexual
    0.93
     сексу
    0.88
     seksual
    0.88
     erotic
    0.83
     sex
    0.83
     sexuales
    0.83
     seks
    0.81
     Sexual
    0.81
     SEX
    0.77
    Sexual
    0.77
    Activations Density 0.090%

    No Known Activations