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. 5-GEMMASCOPE-RES-16K
    6. 14350
    Prev
    Next
    INDEX
    Explanations

    mathematical terms and symbols related to equations, parameters, and theorems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    //
    -0.54
    styleUrls
    -0.52
    DeleteBehavior
    -0.51
     GoogleFonts
    -0.50
    ίδι
    -0.50
     minh
    -0.49
     BoxDecoration
    -0.49
    ThroughAttribute
    -0.47
    yarnpkg
    -0.46
    ]]
    
    -0.45
    POSITIVE LOGITS
    oredCriteria
    0.66
    الإنجليزية
    0.65
     '*':
    0.63
    PS
    0.59
    elemField
    0.59
    ViewImports
    0.59
     mergeFrom
    0.56
     equivo
    0.56
     referenties
    0.54
    webElementXpaths
    0.54
    Activations Density 2.659%

    No Known Activations