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. 6601
    Prev
    Next
    INDEX
    Explanations

    medical terminology and statistical analysis related to health studies

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

    Preceding words of non-English text

    np_acts-logits-general · gemini-2.0-flash

    measurements and enzymes

    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
     vlasy
    -0.62
     vzduchu
    -0.59
     vodou
    -0.58
     kereszt
    -0.57
     łóż
    -0.57
    ýš
    -0.55
    ższych
    -0.55
     przód
    -0.54
     gwaran
    -0.54
     úrov
    -0.54
    POSITIVE LOGITS
     ujednoznacz
    0.89
    Witam
    0.75
     استنادى
    0.74
     nakalista
    0.73
    DeleteBehavior
    0.72
    ViewImports
    0.68
    styleType
    0.67
     Lewandowski
    0.65
    RectangleBorder
    0.64
    Przypisy
    0.63
    Activations Density 0.087%

    No Known Activations