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. 24279
    Prev
    Next
    INDEX
    Explanations

    structural elements and relationships within data arrays and mathematical expressions

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

    indices of numbers

    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
     queſta
    -0.71
    TypedDataSet
    -0.70
    MessageTagHelper
    -0.68
    ThroughAttribute
    -0.67
    UrlResolution
    -0.65
    ReusableCell
    -0.63
     Paglinawan
    -0.63
    RTLR
    -0.62
    richTextPanel
    -0.61
    
    -0.61
    POSITIVE LOGITS
     positions
    0.33
     posiciones
    0.32
    二
    0.29
     pas
    0.29
    gangenheit
    0.29
    <?
    0.28
     chiffres
    0.28
     vá
    0.26
     μά
    0.26
     Geburtstag
    0.25
    Activations Density 0.331%

    No Known Activations