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. 20-GEMMASCOPE-RES-16K
    6. 4828
    Prev
    Next
    INDEX
    Explanations

    elements related to programming syntax and structures

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

    Code loops, specifically "for" loops

    np_acts-logits-general · gemini-2.0-flash

    iteration keyword

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    protoimpl
    -0.88
     resourceCulture
    -0.87
    
    -0.86
    :✨
    -0.83
    GEBURTSDATUM
    -0.82
    脚注の使い方
    -0.80
    Datuak
    -0.79
     שוליים
    -0.78
    ValueStyle
    -0.78
     Италијани
    -0.76
    POSITIVE LOGITS
     for
    2.44
    for
    2.22
     voor
    1.39
     For
    1.39
     для
    1.37
     FOR
    1.36
     untuk
    1.31
    For
    1.29
     für
    1.28
    foreach
    1.19
    Activations Density 0.145%

    No Known Activations