© 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
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 11490
    Prev
    Next
    INDEX
    Explanations

    terms related to Chinese medicine and healthcare systems

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

    preceding Chinese, Japanese, or Korean terms

    np_acts-logits-general · gemini-2.0-flash

    Chinese place names and terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    endorong
    -0.35
    acamata
    -0.34
     Decke
    -0.33
     jüdis
    -0.30
     вести
    -0.30
     nele
    -0.30
    var
    -0.30
     Einstellung
    -0.30
     campagnes
    -0.30
    ıdır
    -0.29
    POSITIVE LOGITS
     للاسماء
    0.80
     ब्रेकडाउन
    0.77
    .*")]
    0.71
    TagMode
    0.68
    Tembelea
    0.66
     Wiktionnaire
    0.66
     للمعارف
    0.65
     getItemCount
    0.65
    AndEndTag
    0.65
     &___
    0.65
    Activations Density 0.038%

    No Known Activations