© 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. 40-GEMMASCOPE-RES-16K
    11. 3384
    Prev
    Next
    INDEX
    Explanations

    terms related to sexual misconduct and harassment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sexuelle
    -0.75
     sexual
    -0.71
     sex
    -0.70
    sexual
    -0.68
     Sexual
    -0.66
     SEX
    -0.66
     Sex
    -0.66
    sex
    -0.62
     sexually
    -0.62
     sexuality
    -0.60
    POSITIVE LOGITS
     assault
    0.50
     orientation
    0.45
     minorities
    0.45
     transmitted
    0.43
     favors
    0.40
    entierung
    0.40
    partner
    0.40
     Orientation
    0.40
     assaulted
    0.39
     partners
    0.39
    Activations Density 0.303%

    No Known Activations