© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 12641
    Prev
    Next
    INDEX
    Explanations

    references to male individuals or the concept of manhood

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

    Follows/is associated with the word "man."

    np_acts-logits-general · gemini-2.0-flash

    man or men as individuals described

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    willi
    -0.46
    totic
    -0.45
     Shimizu
    -0.42
     oblivious
    -0.41
     gratuitous
    -0.40
     dini
    -0.40
    ي
    -0.40
    CCESS
    -0.40
     ignored
    -0.39
     futile
    -0.39
    POSITIVE LOGITS
     man
    1.16
     Man
    1.00
     woman
    0.94
     Woman
    0.91
    Man
    0.91
     homme
    0.91
     men
    0.90
    man
    0.86
     hombre
    0.85
     Men
    0.84
    Activations Density 0.109%

    No Known Activations