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-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 75346
    Prev
    Next
    INDEX
    Explanations

    the occurrence of the command 'continue' in programming contexts

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

    skip or continue

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     QtWidgets
    -0.65
     surla
    -0.58
     MainAxisSize
    -0.57
     SqlDbType
    -0.55
    ToProps
    -0.54
    存于互联网档案馆
    -0.51
    ="@+
    -0.51
    onedDateTime
    -0.50
    AndEndTag
    -0.49
     IBOutlet
    -0.48
    POSITIVE LOGITS
    continue
    0.81
    skip
    0.52
    SKIP
    0.47
     continue
    0.47
     skip
    0.45
    ništvo
    0.42
    Skip
    0.42
     cią
    0.42
     inspección
    0.40
    Next
    0.40
    Activations Density 0.003%

    No Known Activations