© 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. 31766
    Prev
    Next
    INDEX
    Explanations

    patterns or expressions involving regular expressions

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

    regex and code structure

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    PreferredItem
    -0.78
    __":
    -0.59
     MainAxisSize
    -0.59
    centralwidget
    -0.57
     lenker
    -0.57
     actionPerformed
    -0.54
    EndContext
    -0.53
    outState
    -0.52
    SceneManagement
    -0.52
     CSRF
    -0.50
    POSITIVE LOGITS
    (/\
    0.68
     /\.
    0.67
     /\.(
    0.63
    (/^
    0.61
    (/[
    0.59
     /^
    0.58
     /^[
    0.57
    (/
    0.56
    /*
    0.52
    __(/*!
    0.49
    Activations Density 0.006%

    No Known Activations