Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 70832
    Prev
    Next
    INDEX
    Explanations

    references to men and masculinity

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

    man and men

    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
     poza
    -0.40
     kuu
    -0.38
     interrupt
    -0.34
    cross
    -0.33
     cross
    -0.33
    Disconnected
    -0.32
     Silly
    -0.31
    ügel
    -0.31
     annoy
    -0.31
    Interrupt
    -0.31
    POSITIVE LOGITS
     man
    0.86
     men
    0.85
     uomini
    0.82
     homens
    0.75
     hommes
    0.75
    matchCondition
    0.75
     hombres
    0.71
    webElementXpaths
    0.70
     hombre
    0.70
    hommes
    0.69
    Activations Density 0.028%

    No Known Activations