© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 17952
    Prev
    Next
    INDEX
    Explanations

    phrases related to medical disclaimers and advice

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

    advice for medical or legal matters

    np_acts-logits-general · gemini-2.5-flash-lite

    finds disclaimer text that warns the content is for informational/educational purposes only and not a substitute for professional (medical/legal/other) advice or services.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0

    disclaimer and legal/medical boilerplate stating information is for educational purposes only, not professional advice, with cautions like consulting qualified professionals and forward-looking statement notices.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
     незавершена
    -0.57
     resourceCulture
    -0.55
     nahilalakip
    -0.54
    OrNil
    -0.52
    WithIdentifier
    -0.51
    
    -0.51
    énario
    -0.50
    httphttps
    -0.50
    ConstraintMaker
    -0.50
     arşivlendi
    -0.49
    POSITIVE LOGITS
     legal
    0.42
     medical
    0.40
     general
    0.39
     advice
    0.37
    カンド
    0.36
     Gór
    0.34
     lack
    0.34
     vet
    0.34
    enteuer
    0.33
     healing
    0.33
    Activations Density 0.313%

    No Known Activations