© 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. 9813
    Prev
    Next
    INDEX
    Explanations

    mentions of "ward" in various contexts

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

    Ward and warders

    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
     EconPapers
    -0.58
     فريبيس
    -0.55
    ьаж
    -0.53
    TargetException
    -0.52
    KommentareTeilen
    -0.51
    Liza
    -0.50
     Kik
    -0.50
    ifun
    -0.50
     للاسماء
    -0.49
    jeep
    -0.48
    POSITIVE LOGITS
     Ward
    1.17
     ward
    1.15
    Ward
    1.10
     WARD
    1.01
    ward
    0.85
     wards
    0.81
    WARD
    0.71
     Wardrobe
    0.62
    病房
    0.58
     wall
    0.58
    Activations Density 0.003%

    No Known Activations