Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 114026
    Prev
    Next
    INDEX
    Explanations

    tabular data structures or elements

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

    HTML structure tags

    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
     or
    -0.36
     habilidad
    -0.35
     zakon
    -0.33
     identificación
    -0.33
     préférence
    -0.32
     instalación
    -0.32
     prestation
    -0.32
    <eos>
    -0.32
     worth
    -0.31
     programmation
    -0.31
    POSITIVE LOGITS
    ंदीखरीदारी
    0.92
    httphttps
    0.92
     للاسماء
    0.88
     EconPapers
    0.87
    webElementXpaths
    0.85
     <<<<<<<<<<<<<<
    0.82
    Diweddarwch
    0.81
     nahilalakip
    0.79
     propOrder
    0.77
    ScopeManager
    0.75
    Activations Density 0.002%

    No Known Activations