© 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. 53398
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords associated with variable declarations and class definitions

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

    `Tag` or `name` followed by `"="` or `case`

    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
    ChildScrollView
    -0.41
     considérée
    -0.37
     Мексичка
    -0.37
     Schluß
    -0.37
     gráfica
    -0.36
     alignItems
    -0.36
     Capsules
    -0.35
     rağmen
    -0.35
    ieważ
    -0.35
     groupBox
    -0.35
    POSITIVE LOGITS
     للاسماء
    0.79
     ModelExpression
    0.68
     propOrder
    0.61
     beginnetje
    0.59
     autorytatywna
    0.54
    httphttps
    0.54
    urlpatterns
    0.52
    (!__
    0.51
     lenker
    0.49
    حوالہ
    0.49
    Activations Density 0.006%

    No Known Activations