© 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. 106893
    Prev
    Next
    INDEX
    Explanations

    specific biomedical terms and phrases related to types of cells and their roles in health and disease

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

    numbers and descriptors

    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
    InjectAttribute
    -0.34
     Schild
    -0.32
    row
    -0.29
    .*")]
    -0.28
    localctx
    -0.28
    ()?;
    -0.28
    landschaft
    -0.27
    員
    -0.27
     Volk
    -0.27
     house
    -0.27
    POSITIVE LOGITS
     الرياضيه
    0.73
    ########.
    0.60
     purpoſe
    0.58
     ddelwed
    0.57
    addPreferredGap
    0.57
     فريبيس
    0.57
    rungsseite
    0.56
    nologue
    0.55
     spéciaux
    0.54
     NSCoder
    0.54
    Activations Density 0.105%

    No Known Activations