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

    Neuronpedia

    Jacobian LensNEW
    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 - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 4979
    Prev
    Next
    INDEX
    Explanations

    references to "man" and its variations in various contexts

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

    "man" followed by various words and punctuation

    np_acts-logits-general · gemini-2.0-flash

    "man" and "woman"

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    uque
    -0.47
    yll
    -0.42
    OGND
    -0.40
    orios
    -0.40
     كومونز
    -0.40
    ي
    -0.39
     futile
    -0.39
    ylo
    -0.39
     rout
    -0.39
    rieux
    -0.39
    POSITIVE LOGITS
     man
    1.95
     Man
    1.79
    Man
    1.78
    man
    1.66
     MAN
    1.55
    MAN
    1.48
     woman
    1.27
     Woman
    1.25
    マン
    1.21
    Woman
    1.16
    Activations Density 0.148%

    No Known Activations