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. 2472
    Prev
    Next
    INDEX
    Explanations

    syntactical structures related to control flow in programming, particularly conditional statements and loops

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

    Code that includes "break" or "options" statements

    np_acts-logits-general · gemini-2.0-flash

    break 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
     виправивши
    -0.58
    lå
    -0.48
    ]")]
    -0.48
     '{@
    -0.48
     cuantas
    -0.47
    Décès
    -0.47
     Posteriormente
    -0.45
     überhaupt
    -0.44
     zin
    -0.42
    後悔
    -0.41
    POSITIVE LOGITS
    break
    3.14
     break
    3.09
     Break
    2.48
     breaks
    2.43
    Break
    2.22
     BREAK
    2.18
     Breaks
    2.08
    breaks
    1.93
    BREAK
    1.87
     breaking
    1.75
    Activations Density 0.112%

    No Known Activations