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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 5300
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "args" typically associated with programming or function arguments

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

    "args" in main method declarations

    np_acts-logits-general · gemini-2.0-flash

    args parameter in code

    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-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
    EndProject
    -0.52
    devamını
    -0.52
    */),
    -0.51
    expandindo
    -0.50
     ویکی‌پدی
    -0.50
    TintMode
    -0.47
    "]}
    -0.47
    })*/
    -0.47
    ]}"
    -0.46
    tanleria
    -0.46
    POSITIVE LOGITS
     args
    2.39
    args
    1.93
    Args
    1.45
     Args
    1.34
    ARGS
    1.04
    TypeArgs
    0.77
     EventArgs
    0.75
    EventArgs
    0.70
     Arguments
    0.69
     arguments
    0.63
    Activations Density 0.024%

    No Known Activations