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

    Neuronpedia

    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. 10441
    Prev
    Next
    INDEX
    Explanations

    pairs of closing parentheses in code syntax or structure

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

    Code snippets and code-related syntax

    np_acts-logits-general · gemini-2.0-flash

    parentheses and code blocks

    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
     ""
    -0.60
    AccessorTable
    -0.59
    DataPropertyName
    -0.57
     ''
    -0.55
    ("");
    -0.52
    ();
    -0.51
     bày
    -0.51
     ?>
    -0.49
    ('');
    -0.48
    ]();
    -0.47
    POSITIVE LOGITS
     propOrder
    0.81
     defaultstate
    0.67
    دانشنامهٔ
    0.66
     {
    0.63
    DeleteBehavior
    0.61
    はじめに
    0.61
    PerformLayout
    0.60
    🏾
    0.59
    tonsoft
    0.59
    CodeAttribute
    0.58
    Activations Density 0.066%

    No Known Activations