© 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. 31-GEMMASCOPE-RES-131K
    11. 38858
    Prev
    Next
    INDEX
    Explanations

    explicit language and phrases reflecting frustration or aggression

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

    bitch, nigga, and motherfucker

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    QMetaType
    -0.56
    sena
    -0.53
    tagHelperRunner
    -0.52
    MemoryWarning
    -0.48
    onOptions
    -0.47
    RenderAtEndOf
    -0.45
     Nasal
    -0.45
    epam
    -0.44
     فريبيس
    -0.43
    topt
    -0.43
    POSITIVE LOGITS
     bitch
    1.13
     bitches
    1.00
    bitch
    0.91
     motherfucker
    0.88
    Bitch
    0.85
     Bitch
    0.85
     nigga
    0.67
     niggas
    0.60
     fucker
    0.58
     shit
    0.52
    Activations Density 0.046%

    No Known Activations