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. 2456
    Prev
    Next
    INDEX
    Explanations

    occurrences of the keyword 'while' in various contexts, indicating loops in code

    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
    IMPORTED
    -0.66
     './../
    -0.56
     perhaps
    -0.54
     @"
    -0.54
    umenter
    -0.53
     '../../../../
    -0.50
    /-
    -0.50
     Abp
    -0.50
     algún
    -0.48
     vielleicht
    -0.47
    POSITIVE LOGITS
    while
    1.60
    WHILE
    1.07
     while
    0.97
    mientras
    0.94
    basicConfig
    0.92
     WHILE
    0.91
     enquanto
    0.88
     whilst
    0.85
    Mientras
    0.85
     дописавши
    0.83
    Activations Density 0.046%

    No Known Activations