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. 12950
    Prev
    Next
    INDEX
    Explanations

    programming-related components and structure

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

    Code, parentheses, or commas

    np_acts-logits-general · gemini-2.0-flash

    App loads, infectious diseases

    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
     }{@
    -0.83
    TargetException
    -0.78
     &___
    -0.77
     propOrder
    -0.73
     StringTokenizer
    -0.70
     PhpStorm
    -0.67
     contextLoads
    -0.67
    rungsseite
    -0.67
    URLException
    -0.67
     StringBuffer
    -0.67
    POSITIVE LOGITS
    \{\\
    0.56
     styled
    0.56
     SwiftUI
    0.52
    styled
    0.46
    Stateless
    0.45
     showcase
    0.45
    نم
    0.44
     μον
    0.44
     components
    0.44
     Showcase
    0.44
    Activations Density 0.015%

    No Known Activations