© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 13438
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to traditional Chinese medicine and its practices

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

    Oriental or Chinese medicine

    np_acts-logits-general · gemini-2.0-flash

    chinese and oriental medicine diagnosis

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     sm
    -0.35
    Editing
    -0.32
     Gep
    -0.32
     بوس
    -0.31
     آپ
    -0.31
     nem
    -0.31
    ultimate
    -0.31
     az
    -0.30
     communiquer
    -0.30
     gel
    -0.30
    POSITIVE LOGITS
    RectangleBorder
    0.63
    PMailer
    0.63
    berdayakan
    0.63
    AndEndTag
    0.59
    RefNanny
    0.59
    BufferException
    0.58
    principalColumn
    0.57
    TargetException
    0.57
     resourceCulture
    0.56
    toMatchSnapshot
    0.56
    Activations Density 0.174%

    No Known Activations