© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 67227
    Prev
    Next
    INDEX
    Explanations

    terms related to gender characteristics and their representations

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

    feminine and masculine distinctions

    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
    väg
    -0.48
     previs
    -0.47
     Decke
    -0.46
     Anexo
    -0.46
     passage
    -0.45
    Lihat
    -0.44
    梗
    -0.44
     stället
    -0.44
     provis
    -0.43
     Hift
    -0.43
    POSITIVE LOGITS
     Feminine
    0.96
     feminine
    0.94
     femininity
    0.81
     feminino
    0.69
     femeninos
    0.69
     feminina
    0.68
     femininas
    0.66
     FEM
    0.65
     femininos
    0.65
     masculine
    0.64
    Activations Density 0.005%

    No Known Activations