© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 82596
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "throws" in various contexts related to exceptions and error handling in programming

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

    throwing exceptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    Personendaten
    -0.73
     Majefty
    -0.66
    mobileqq
    -0.66
    intenant
    -0.65
     ExecuteAsync
    -0.64
     dAtA
    -0.63
    majánló
    -0.61
    Personensuche
    -0.61
     intptr
    -0.61
     surla
    -0.57
    POSITIVE LOGITS
    throws
    2.80
     throws
    1.39
    Throws
    1.24
    throw
    1.18
     Throws
    1.16
    throwing
    1.01
    threw
    0.93
     throwing
    0.92
    Throwing
    0.91
     Throwing
    0.89
    Activations Density 0.002%

    No Known Activations