© 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
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 12486
    Prev
    Next
    INDEX
    Explanations

    references to medical conditions or terminology related to diabetes and its implications

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

    preceding capitalized words

    np_acts-logits-general · gemini-2.0-flash

    type 2 diabetes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ing
    -0.47
     Com
    -0.46
    esthetics
    -0.46
    脚注
    -0.45
    ted
    -0.45
     enda
    -0.44
    kran
    -0.44
    θεια
    -0.43
    зирован
    -0.43
    മ്പ
    -0.43
    POSITIVE LOGITS
    RenderAtEndOf
    0.72
    SourceChecksum
    0.62
    usercontent
    0.61
    الحياه
    0.60
     propOrder
    0.58
    bcryptjs
    0.58
    AndEndTag
    0.56
    MIDDLEWARE
    0.55
     auroit
    0.54
     avoient
    0.54
    Activations Density 1.691%

    No Known Activations