© 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 EvalsExportsinterp-engineNEWAPI 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. 32669
    Prev
    Next
    INDEX
    Explanations

    references to gender and possibly relationships

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

    gendered roles and actions

    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
    主题
    -0.33
    simpleType
    -0.32
    :
    -0.31
    ęty
    -0.30
     prestasi
    -0.29
     erreichen
    -0.29
     EconPapers
    -0.28
     bereiken
    -0.28
     nacer
    -0.28
     tarihi
    -0.27
    POSITIVE LOGITS
     ſte
    0.78
     ſta
    0.77
    <unused52>
    0.77
    <unused79>
    0.77
    <unused16>
    0.77
    <unused14>
    0.77
    <unused43>
    0.76
    <unused68>
    0.76
    <unused41>
    0.76
    <unused8>
    0.76
    Activations Density 0.006%

    No Known Activations