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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 90
    Prev
    Next
    INDEX
    Explanations

    quantitative measurements and discussions related to health outcomes, particularly in the context of diabetes and medical interventions

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

    Numerical change or difference

    np_acts-logits-general · gemini-2.0-flash

    percentage, points, price changes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     StatefulWidget
    -0.57
    IntoConstraints
    -0.56
    허
    -0.53
     فريبيس
    -0.50
    +#+#
    -0.48
     paro
    -0.47
     ExecuteAsync
    -0.45
     setuptools
    -0.45
     Meri
    -0.45
    Вт
    -0.45
    POSITIVE LOGITS
     tambahan
    0.77
     difference
    0.73
     aggiun
    0.70
     lisää
    0.70
     supplémentaire
    0.66
     adicional
    0.66
    AddTagHelper
    0.66
     added
    0.65
    تقاوى
    0.64
     незавершена
    0.63
    Activations Density 0.636%

    No Known Activations