Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 92260
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to early diagnosis and intervention in medical contexts

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

    early detection and prevention

    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
    enumii
    -0.52
     totalSupply
    -0.46
    Xna
    -0.44
    ixote
    -0.44
     carbonates
    -0.43
    aronder
    -0.43
    GenerationType
    -0.42
     intStringLen
    -0.42
     makeStyles
    -0.40
    Espèce
    -0.40
    POSITIVE LOGITS
     early
    0.54
     detection
    0.53
    Early
    0.52
     temprana
    0.52
     Early
    0.48
     detectar
    0.48
    early
    0.48
     temprano
    0.47
     EARLY
    0.47
     diagnosis
    0.46
    Activations Density 0.024%

    No Known Activations