© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 104365
    Prev
    Next
    INDEX
    Explanations

    descriptions of sexual activity and physical intimacy

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

    Text fragments describing sexual acts or containing explicit sexual content, often including anatomical terms, body parts, and descriptions of intimate activities.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
     surla
    -0.60
    ロウィン
    -0.60
     invokingState
    -0.57
    ----</
    -0.57
     erſt
    -0.56
     $_(
    -0.56
    rungsseite
    -0.55
    PyExc
    -0.55
     betweenstory
    -0.55
    ագրություններ
    -0.55
    POSITIVE LOGITS
     orgas
    0.31
    lack
    0.30
     hacerle
    0.28
    enterOuterAlt
    0.28
     masturb
    0.28
     orgasm
    0.27
     pipes
    0.27
    labor
    0.27
     ASS
    0.26
     sè
    0.26
    Activations Density 0.102%

    No Known Activations