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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 49870
    Prev
    Next
    INDEX
    Explanations

    function and method declarations in programming contexts

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

    code syntax,especially C++ templates and PHP helpers

    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
     valentín
    -0.45
    สือ
    -0.41
     garantías
    -0.40
     trámite
    -0.40
     fermée
    -0.38
     mukaan
    -0.37
     šķ
    -0.37
     betweenstory
    -0.36
     tvá
    -0.36
     prestazioni
    -0.36
    POSITIVE LOGITS
    __(/*!
    0.86
     CreateTagHelper
    0.73
     հղումներ
    0.71
    SequentialGroup
    0.67
     المعيارى
    0.65
    WEBPACK
    0.64
     informée
    0.61
    脚注の使い方
    0.60
     surla
    0.60
    RTGC
    0.59
    Activations Density 0.006%

    No Known Activations