© 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. 104958
    Prev
    Next
    INDEX
    Explanations

    symbols and keywords associated with mathematics and programming

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

    math, numbers, and symbols

    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
     olmayan
    -0.43
    Traducción
    -0.40
    webElementXpaths
    -0.38
    Redaktion
    -0.38
    i
    -0.37
    ufficio
    -0.36
     aynı
    -0.36
    <strong>
    -0.36
    <em>
    -0.35
    «
    -0.35
    POSITIVE LOGITS
     ब्रेकडाउन
    0.86
     يتيمه
    0.76
     الحره
    0.74
    లాలు
    0.69
     kasarigan
    0.66
     zwiſchen
    0.63
    Chham
    0.62
    存于互联网档案馆
    0.61
     שוליים
    0.59
     nahilalakip
    0.59
    Activations Density 0.002%

    No Known Activations