© 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. 104811
    Prev
    Next
    INDEX
    Explanations

    occurrences of code-related syntax and structure, particularly braces and import statements

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

    <start_of_turn>user

    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
    -0.39
     noDo
    -0.34
    Ӕ
    -0.32
     ModelRenderer
    -0.32
    Хьажоргаш
    -0.31
    بوابة
    -0.30
     Empieza
    -0.30
    tagext
    -0.30
    velocityX
    -0.29
     himo
    -0.28
    POSITIVE LOGITS
     resourceCulture
    0.58
    :✨
    0.57
    gbaar
    0.57
     ſchon
    0.56
    <unused15>
    0.55
     erſten
    0.55
     initComponents
    0.55
    elow
    0.54
    EndInit
    0.54
    rencies
    0.54
    Activations Density 0.002%

    No Known Activations