© 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. 8347
    Prev
    Next
    INDEX
    Explanations

    phrases indicating increases or changes in quantities

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

    Multiplication or scaling factors

    np_acts-logits-general · gemini-2.0-flash

    numbers followed by times or fold

    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
    ########.
    -0.88
    ContentLoaded
    -0.54
    Geplaatst
    -0.50
    IntoConstraints
    -0.50
     bast
    -0.50
    qrstuvwxyz
    -0.49
     BeautifulSoup
    -0.49
    conio
    -0.49
    __":
    -0.47
    chila
    -0.46
    POSITIVE LOGITS
     double
    1.39
     threefold
    1.37
     times
    1.34
     twice
    1.33
     quadruple
    1.30
     twofold
    1.29
     triple
    1.28
    double
    1.27
     DOUBLE
    1.22
    倍
    1.21
    Activations Density 0.549%

    No Known Activations