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. 1193
    Prev
    Next
    INDEX
    Explanations

    instances of the word "break" in programming contexts

    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
    Ārējās
    -0.49
     geisti
    -0.47
    ido
    -0.46
    the
    -0.45
    really
    -0.44
     المعيارى
    -0.43
    IDO
    -0.43
     decent
    -0.43
    -/
    -0.42
     nearly
    -0.42
    POSITIVE LOGITS
    break
    1.82
     break
    1.34
     Break
    1.23
     endforeach
    1.21
    ArgsConstructor
    1.21
     BREAK
    1.20
    endphp
    1.18
    BREAK
    1.14
     CreateTagHelper
    1.14
    Break
    1.13
    Activations Density 0.022%

    No Known Activations