© 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. 8644
    Prev
    Next
    INDEX
    Explanations

    key structural elements in programming or technical documents

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

    C preprocessor directives (#define) and constants

    np_acts-logits-general · gemini-2.0-flash

    programming code definitions

    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
     [:
    -0.49
    tdessen
    -0.49
     finally
    -0.47
     newVal
    -0.43
    frem
    -0.41
    جمعیت
    -0.40
     Himo
    -0.40
     como
    -0.40
     selectively
    -0.39
     InkWell
    -0.39
    POSITIVE LOGITS
    AndEndTag
    0.95
    EDEFAULT
    0.92
    UnusedPrivate
    0.89
    IntoConstraints
    0.86
    rungsseite
    0.83
    Autoritní
    0.80
    WindowConstants
    0.79
     MAX
    0.78
    sidemargin
    0.78
     default
    0.78
    Activations Density 0.300%

    No Known Activations