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. 12755
    Prev
    Next
    INDEX
    Explanations

    technical terms and variables related to programming and system architectures

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

    Code-related tokens (e.g., variable names, definitions)

    np_acts-logits-general · gemini-2.0-flash

    variable definitions or assignments

    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
     للمعارف
    -0.82
     consultato
    -0.49
    strona
    -0.49
     connais
    -0.45
    ɝ
    -0.43
    ssysteme
    -0.43
    ادل
    -0.42
    ɜ
    -0.41
     poissons
    -0.41
    ProductType
    -0.41
    POSITIVE LOGITS
    tonsoft
    0.82
    stateProvider
    0.76
    setVerticalGroup
    0.76
     AspNetCore
    0.74
     otomatig
    0.73
     հղումներ
    0.73
    reportWebVitals
    0.72
     مرئيه
    0.70
     Administrativna
    0.66
    헌
    0.66
    Activations Density 0.274%

    No Known Activations