© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 9536
    Prev
    Next
    INDEX
    Explanations

    mentions of sexual harassment and related complaints

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

    Sexual abuse, harassment, and rape

    np_acts-logits-general · gemini-2.0-flash

    sexual abuse and rape allegations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DispatchToProps
    -0.78
    providedIn
    -0.69
    TagMode
    -0.67
     getItemCount
    -0.66
    !*\
    -0.60
     numberWith
    -0.59
     Nebu
    -0.58
    verwijspagina
    -0.57
    cetin
    -0.55
    hysema
    -0.55
    POSITIVE LOGITS
     sexual
    1.13
     Sexual
    1.07
    Sexual
    0.97
    sexual
    0.86
     Rape
    0.85
    Rape
    0.82
     rape
    0.80
     sexuelle
    0.78
     sexually
    0.76
     SEX
    0.72
    Activations Density 0.272%

    No Known Activations