© 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. 9-GEMMASCOPE-RES-131K
    11. 35465
    Prev
    Next
    INDEX
    Explanations

    terms indicating critical medical conditions or severe impairments

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

    medical condition severity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    autant
    -0.36
     ото
    -0.35
    Nap
    -0.34
    p
    -0.34
    เส
    -0.33
    PM
    -0.33
    fp
    -0.32
    –
    -0.32
    ip
    -0.31
    {'
    -0.31
    POSITIVE LOGITS
    GEBURTSDATUM
    0.77
     يتيمه
    0.76
     propOrder
    0.72
    Diweddarwch
    0.71
    ftagPool
    0.69
    mybatisplus
    0.68
    webElementXpaths
    0.68
    verwijspagina
    0.65
    TagMode
    0.65
    ConstraintMaker
    0.65
    Activations Density 0.131%

    No Known Activations