Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 3448
    Prev
    Next
    INDEX
    Explanations

    instances of the "break" statement in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     veulent
    -0.39
    niña
    -0.37
     voulait
    -0.36
    Мои
    -0.35
     photographic
    -0.35
    }`).
    -0.35
    ">
    
    
    -0.35
    |}{\
    -0.34
    みたら
    -0.34
    ']],
    -0.33
    POSITIVE LOGITS
    break
    2.25
     break
    1.72
     Break
    1.55
    Break
    1.52
    BREAK
    1.38
     BREAK
    1.31
    breaks
    1.22
     breaks
    1.19
     Breaks
    1.10
     endwhile
    0.87
    Activations Density 0.065%

    No Known Activations