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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 46886
    Prev
    Next
    INDEX
    Explanations

    terms related to sexual conduct and harassment

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

    sexual conduct and harassment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
     Dimensiones
    -0.54
     Theorie
    -0.54
    ejemplo
    -0.53
    đi
    -0.52
     mess
    -0.50
     Durchmesser
    -0.50
    ึ้น
    -0.49
    ntö
    -0.49
     tärke
    -0.49
     Gewicht
    -0.49
    POSITIVE LOGITS
     Sexual
    1.02
    Sexual
    0.99
     sexual
    0.95
    sexual
    0.89
    osexual
    0.79
     sexually
    0.71
    neurial
    0.69
     seksual
    0.67
     сексу
    0.65
    Musical
    0.60
    Activations Density 0.007%

    No Known Activations