© 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. 22-GEMMASCOPE-RES-16K
    11. 12452
    Prev
    Next
    INDEX
    Explanations

    numbers and statistics related to sports performances

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

    Accuracy of throws or shots

    np_acts-logits-general · gemini-2.0-flash

    accuracy and misses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ValueStyle
    -0.80
     الاطلاع
    -0.66
    pexpr
    -0.65
     ujednoznacz
    -0.58
    ValueGenerated
    -0.55
    EndInit
    -0.55
    TabIndex
    -0.51
    sizeCache
    -0.49
    BeginInit
    -0.48
     ویکی‌پدیای
    -0.48
    POSITIVE LOGITS
     misses
    0.80
     accuracy
    0.76
     missed
    0.74
     inaccuracy
    0.69
     accurate
    0.66
     Accuracy
    0.66
    Missed
    0.66
     rico
    0.65
    Accuracy
    0.64
     akurat
    0.64
    Activations Density 0.139%

    No Known Activations