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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 91509
    Prev
    Next
    INDEX
    Explanations

    instances of the term "InterruptedException" and related time measurements in code snippets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    ########.
    -0.72
    ckså
    -0.58
     informée
    -0.55
     وتسجيلات
    -0.50
    colha
    -0.49
     onOptions
    -0.49
     surla
    -0.49
    BindView
    -0.47
    providedIn
    -0.47
    abestanden
    -0.47
    POSITIVE LOGITS
    ruptedException
    2.34
    AccessException
    0.70
    TargetException
    0.56
    ServiceException
    0.56
    BlockingQueue
    0.52
     interrup
    0.51
     interrupted
    0.48
    TimeUnit
    0.47
     SQLException
    0.47
    WaitGroup
    0.47
    Activations Density 0.000%

    No Known Activations