© 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. 1103
    Prev
    Next
    INDEX
    Explanations

    operations related to incrementing and modifying values in code

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

    Code snippets containing "+=" or similar operators

    np_acts-logits-general · gemini-2.0-flash

    adding or subtracting code snippets

    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
    EndProject
    -0.61
     المعيارى
    -0.51
    ul
    -0.50
    دیگر
    -0.48
    -
    -0.47
    ăl
    -0.46
    jsxFileName
    -0.46
     فريبيس
    -0.46
    ity
    -0.45
    cristo
    -0.45
    POSITIVE LOGITS
     +=
    1.00
     }}"></
    0.91
    tagHelperRunner
    0.90
    jectures
    0.86
    iented
    0.84
    AddTagHelper
    0.81
    GeneratedValue
    0.81
    ScopeManager
    0.80
    utdown
    0.77
     -=
    0.76
    Activations Density 0.032%

    No Known Activations