© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 111711
    Prev
    Next
    INDEX
    Explanations

    references to utility functions or classes in a programming context

    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
    prefixer
    -0.59
    ckså
    -0.59
    WebControls
    -0.58
    IntoConstraints
    -0.52
     geweest
    -0.51
    transQ
    -0.50
    __(/*!
    -0.50
    esgue
    -0.50
    AntiForgeryToken
    -0.49
    getreten
    -0.48
    POSITIVE LOGITS
    utils
    1.52
     utils
    1.27
    Util
    0.71
     Util
    0.68
     Utils
    0.65
    Utils
    0.65
    util
    0.57
    FileUtils
    0.57
     utilities
    0.56
     utility
    0.56
    Activations Density 0.001%

    No Known Activations