© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14775
    Prev
    Next
    INDEX
    Explanations

    instances of structured programming syntax and code-related elements

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

    Code snippets or program code

    np_acts-logits-general · gemini-2.0-flash

    closing code blocks

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    -0.87
    featureID
    -0.68
    rungsseite
    -0.67
    :✨
    -0.65
    الحياه
    -0.65
    DockStyle
    -0.65
    MLLoader
    -0.62
     EconPapers
    -0.61
    تقاوى
    -0.58
     المعيارى
    -0.57
    POSITIVE LOGITS
    存于互联网档案馆
    0.50
     Gorb
    0.43
    WriteLiteral
    0.41
    তথ্যসূত্র
    0.41
    awtextra
    0.40
    maßen
    0.40
     finally
    0.40
    .
    0.39
    jaus
    0.39
     ско
    0.39
    Activations Density 0.186%

    No Known Activations