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
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 335
    Prev
    Next
    INDEX
    Explanations

    patterns and methods in programming scripts, particularly related to jQuery functions

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

    jQuery and web development-related code fragments and functions.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    balleur
    -0.65
     &___
    -0.62
    ValueStyle
    -0.62
    Tembelea
    -0.61
    BagLayout
    -0.57
     utafitiHapana
    -0.54
    ]")]
    -0.54
    Personensuche
    -0.54
    ември
    -0.53
    getElementById
    -0.52
    POSITIVE LOGITS
    GOTREF
    0.63
    jquery
    0.58
     jQuery
    0.50
     jquery
    0.47
    jQuery
    0.45
     ModelExpression
    0.43
     $("<
    0.39
     desperately
    0.38
     $('<
    0.38
    äume
    0.38
    Activations Density 0.154%

    No Known Activations