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. 19-GEMMASCOPE-RES-16K
    6. 2782
    Prev
    Next
    INDEX
    Explanations

    code syntax and structure, particularly related to function and operator definitions in programming languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Integer
    -0.52
     String
    -0.51
    ié
    -0.50
     Integer
    -0.47
     feel
    -0.46
    integer
    -0.46
     thực
    -0.45
    String
    -0.45
    éndez
    -0.44
    の本
    -0.44
    POSITIVE LOGITS
    const
    1.19
     const
    1.09
     autorytatywna
    0.98
    DeleteBehavior
    0.87
     ModelExpression
    0.75
     AssemblyTitle
    0.72
     CreateTagHelper
    0.71
    :✨
    0.71
    withstanding
    0.69
     ostavi
    0.68
    Activations Density 0.144%

    No Known Activations