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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 15735
    Prev
    Next
    INDEX
    Explanations

    terms related to heart rate monitoring and health tracking technology

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

    data analysis and measurement

    np_acts-logits-general · gemini-2.0-flash

    monitoring and tracking data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Normdatei
    -0.64
    ########.
    -0.64
     définiti
    -0.64
     mourut
    -0.63
     étoit
    -0.63
     WebDriverWait
    -0.63
     Мексичка
    -0.62
     rapides
    -0.61
     betweenstory
    -0.61
     prisonniers
    -0.60
    POSITIVE LOGITS
     data
    0.95
     monitoring
    0.91
     tracking
    0.90
     analytics
    0.86
     Data
    0.79
     monitor
    0.77
     Monitoring
    0.77
     trackers
    0.76
     tracker
    0.75
     TRACK
    0.75
    Activations Density 0.352%

    No Known Activations