© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 11749
    Prev
    Next
    INDEX
    Explanations

    mentions of romantic or extramarital affairs

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

    affair, affairs, revenge

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Lenti
    -0.60
    хьтан
    -0.59
     Crunchy
    -0.58
     Optimus
    -0.58
     ✭✭
    -0.57
    Timo
    -0.56
    Lucas
    -0.56
    IntoConstraints
    -0.56
     Timo
    -0.55
     Bluestacks
    -0.55
    POSITIVE LOGITS
     affair
    1.77
     Affair
    1.56
     affaire
    0.88
    affaire
    0.82
     affairs
    0.71
    Aff
    0.71
     Affairs
    0.63
    aff
    0.63
     AFF
    0.61
     affaires
    0.61
    Activations Density 0.002%

    No Known Activations