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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 11-GEMMASCOPE-RES-16K
    6. 6605
    Prev
    Next
    INDEX
    Explanations

    elements of code syntax and references to programming elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    XDECREF
    -0.52
     faltar
    -0.50
     minOccurs
    -0.48
    rest
    -0.47
     المعيارى
    -0.47
    GetEnumerator
    -0.47
     présidenti
    -0.47
    lendir
    -0.46
    rawtypes
    -0.45
    jooq
    -0.45
    POSITIVE LOGITS
    ViewImports
    0.68
     שוליים
    0.66
    WithMany
    0.66
     ویکی‌پدیای
    0.62
    CloseOperation
    0.61
    Tembelea
    0.60
    styleUrls
    0.59
     honour
    0.58
    ANSA
    0.57
    ProgressHUD
    0.57
    Activations Density 0.149%

    No Known Activations