© 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. 11151
    Prev
    Next
    INDEX
    Explanations

    symbols and special characters, often associated with programming or markup language syntax

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

    Code comments and related symbols

    np_acts-logits-general · gemini-2.0-flash

    code comments

    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
     ExecuteAsync
    -0.96
    GeoNames
    -0.94
    tagHelperRunner
    -0.93
     photolibrary
    -0.91
     doubtnut
    -0.88
     ་་
    -0.88
    .");
    -0.86
    OGND
    -0.85
    SharedDtor
    -0.84
    IntoConstraints
    -0.83
    POSITIVE LOGITS
     The
    1.19
     These
    0.98
     This
    0.97
     Note
    0.96
     We
    0.90
     NOTE
    0.81
     -
    0.81
     A
    0.80
     And
    0.80
     To
    0.80
    Activations Density 0.196%

    No Known Activations