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. 30346
    Prev
    Next
    INDEX
    Explanations

    terms related to medical devices for monitoring heart rate

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

    diagnostic vital signs monitoring

    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
    othelioma
    -0.39
    UpdateCommand
    -0.39
     doInBackground
    -0.38
    FormTagHelper
    -0.37
    éez
    -0.36
    Karriere
    -0.35
     vettoriale
    -0.35
    RotationOrder
    -0.35
     hinweg
    -0.35
    ;'>
    -0.35
    POSITIVE LOGITS
    Autoritní
    0.57
     Diagnos
    0.57
    zzleHttp
    0.55
     diagno
    0.54
     diagnostic
    0.54
     diagnosis
    0.51
    Vitals
    0.51
     diagnoses
    0.51
     diagnose
    0.48
     healthcare
    0.48
    Activations Density 0.056%

    No Known Activations