© 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. 105998
    Prev
    Next
    INDEX
    Explanations

    formatting elements such as figures, tables, and equations in scientific documents

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

    figures with labels and layers

    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
     Numerade
    -0.40
    unistd
    -0.34
     eren
    -0.34
    オリ
    -0.33
     things
    -0.33
     bagay
    -0.33
    ässe
    -0.33
    Footer
    -0.33
     Station
    -0.32
     Aujourd
    -0.32
    POSITIVE LOGITS
    +#+#
    0.88
    QMetaType
    0.62
    IsContent
    0.61
    ftagPool
    0.60
    verwijspagina
    0.57
    脚注の使い方
    0.57
    ValueStyle
    0.56
     demografica
    0.56
    rungsseite
    0.56
     Вікі
    0.54
    Activations Density 0.096%

    No Known Activations