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

    Neuronpedia

    APICircuit 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. 12665
    Prev
    Next
    INDEX
    Explanations

    log messages and error handling in code

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

    Log messages: info, debug, error, warn

    np_acts-logits-general · gemini-2.0-flash

    log statements opening parenthesis

    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
    IVEREF
    -0.58
    ecraft
    -0.56
    engah
    -0.56
     payé
    -0.55
    ArgsConstructor
    -0.54
     урна
    -0.53
    matthew
    -0.53
     essais
    -0.52
    uesday
    -0.52
    requireNonNull
    -0.52
    POSITIVE LOGITS
     minOccurs
    0.69
    verwijspagina
    0.62
    conio
    0.58
    LayoutConstraint
    0.53
     StringBuffer
    0.52
     retire
    0.51
     FY
    0.48
     BigDecimal
    0.48
    脚注の使い方
    0.47
    Literals
    0.47
    Activations Density 0.116%

    No Known Activations