© 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
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 543
    Prev
    Next
    INDEX
    Explanations

    instances of mathematical notation and programming-related syntax

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

    complex mathematical and programming notation, especially involving code snippets and mathematical equations.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
     estekak
    -0.57
    ConstraintLayout
    -0.55
     GlobalKey
    -0.53
     ganchillo
    -0.52
    LayoutPanel
    -0.51
    delwed
    -0.51
    bodyParser
    -0.51
    aarrggbb
    -0.50
     Verlust
    -0.50
    Hentet
    -0.49
    POSITIVE LOGITS
     quæ
    0.36
    transQ
    0.35
     kohdetta
    0.34
     ſch
    0.33
    ⓧ
    0.33
    astéroïdes
    0.32
    Walk
    0.31
    SUD
    0.31
     Walk
    0.31
     EnglishChoose
    0.31
    Activations Density 0.317%

    No Known Activations