© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 120445
    Prev
    Next
    INDEX
    Explanations

    references to Chinese and Oriental medicine concepts and diagnostic practices

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

    oriental medicine and acupuncture

    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
     Hinsicht
    -0.52
    Примітки
    -0.50
     ağır
    -0.47
     hinweg
    -0.47
     propTypes
    -0.46
     jeito
    -0.46
     Annahme
    -0.45
     voluto
    -0.44
     disambiguazione
    -0.44
    errar
    -0.43
    POSITIVE LOGITS
    upuncture
    1.52
     Acupuncture
    1.20
     acupuncture
    1.18
    灸
    0.57
    鍼
    0.56
    RectangleBorder
    0.54
    encodeWith
    0.50
    untura
    0.47
     Needle
    0.46
    upun
    0.45
    Activations Density 0.004%

    No Known Activations