© 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-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 16310
    Prev
    Next
    INDEX
    Explanations

    occurrences of parentheses and their context in programming syntax

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

    Opening parenthesis in code

    np_acts-logits-general · gemini-2.0-flash

    org.apache.commons.math

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    .
    -0.98
    ,
    -0.94
     O
    -0.86
     das
    -0.82
     U
    -0.81
     H
    -0.79
     in
    -0.79
     G
    -0.79
    -
    -0.79
     die
    -0.78
    POSITIVE LOGITS
     myſelf
    1.54
     itſelf
    1.51
     pleaſure
    1.50
     occaf
    1.45
     purpoſe
    1.43
     fubject
    1.41
     poffible
    1.40
     themſelves
    1.40
     Majefty
    1.40
     greateſt
    1.39
    Activations Density 0.471%

    No Known Activations