© 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-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 15288
    Prev
    Next
    INDEX
    Explanations

    terms related to cardiac health and arrhythmias

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

    Cardiac electrophysiology/arrhythmias

    np_acts-logits-general · gemini-2.0-flash

    cardiac arrhythmias ECG and EEG

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    uesta
    -0.48
     Cas
    -0.48
     connexe
    -0.44
     cas
    -0.42
    Cas
    -0.42
     cast
    -0.41
     Cast
    -0.41
    شهاد
    -0.41
    azin
    -0.41
     administrativos
    -0.40
    POSITIVE LOGITS
    tagHelperRunner
    0.97
     EEG
    0.88
     electrodes
    0.85
     Electrical
    0.81
     Electro
    0.80
     electrical
    0.80
     rhythm
    0.77
     rhythms
    0.76
     Elekt
    0.76
     electro
    0.76
    Activations Density 0.687%

    No Known Activations