© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 20078
    Prev
    Next
    INDEX
    Explanations

    references to gender, specifically focusing on the terms "men," "women," and various contexts relating to gender distinctions

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

    men and women

    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
     a
    -0.64
    lass
    -0.63
     Rado
    -0.61
    patch
    -0.60
     Kamp
    -0.59
     parcel
    -0.59
     Patch
    -0.58
     Ressource
    -0.58
     Canton
    -0.57
     Eberhard
    -0.56
    POSITIVE LOGITS
    Men
    0.66
    WOMEN
    0.65
    Women
    0.60
     men
    0.59
     Men
    0.58
    emen
    0.55
     Brethren
    0.54
    women
    0.53
     women
    0.51
    thren
    0.51
    Activations Density 0.041%

    No Known Activations