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. 2-GEMMASCOPE-RES-16K
    6. 2101
    Prev
    Next
    INDEX
    Explanations

    variable names or identifiers within equations or data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    webElementXpaths
    -0.68
    :✨
    -0.56
     außer
    -0.52
     betweenstory
    -0.50
    >-->
    -0.48
     saka
    -0.47
    InitStruct
    -0.47
    tagHelperRunner
    -0.46
    ])[
    -0.44
    entlichen
    -0.43
    POSITIVE LOGITS
    
    0.76
     RoutedEventArgs
    0.70
     AssemblyCulture
    0.69
    DoubleQuotes
    0.69
     DbContext
    0.68
    GraphicsUnit
    0.67
     Dernière
    0.66
    PhysRev
    0.65
    HostException
    0.65
    theim
    0.64
    Activations Density 0.531%

    No Known Activations