© 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. 15832
    Prev
    Next
    INDEX
    Explanations

    numerical data, particularly related to sports statistics and events

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

    preceding verbs

    np_acts-logits-general · gemini-2.0-flash

    goals achieved

    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
    ΟΣ
    -0.52
    uerre
    -0.49
    NewGuid
    -0.48
    SPJ
    -0.47
     lượng
    -0.47
    uracy
    -0.46
    weise
    -0.46
     perio
    -0.45
    urized
    -0.45
     Dur
    -0.45
    POSITIVE LOGITS
     ویکی‌پدیا
    0.92
     Damit
    0.74
    Damit
    0.71
     solidif
    0.69
     solidify
    0.67
    Tikang
    0.65
     decret
    0.64
     cemented
    0.62
    これで
    0.62
     doInBackground
    0.61
    Activations Density 0.153%

    No Known Activations