© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8276
    Prev
    Next
    INDEX
    Explanations

    quantitative measurements and statistical data related to various subjects

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

    Numbers followed by commas or "thousand", "million"

    np_acts-logits-general · gemini-2.0-flash

    large quantities and numbers

    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
    şiv
    -0.61
    delning
    -0.58
     Chwiliwch
    -0.52
    romycin
    -0.49
    holdet
    -0.48
    WriteLiteral
    -0.48
    unjukkan
    -0.47
     cạnh
    -0.47
    ėse
    -0.47
    おすすめです
    -0.47
    POSITIVE LOGITS
     (!)
    0.87
     total
    0.80
    (!)
    0.79
     hundred
    0.79
     thousand
    0.77
    TagMode
    0.77
     acres
    0.72
     souls
    0.70
     pieces
    0.69
     человек
    0.68
    Activations Density 0.358%

    No Known Activations