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

    Neuronpedia

    Jacobian LensNEW
    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. 6266
    Prev
    Next
    INDEX
    Explanations

    the beginning of new sections or paragraphs in a text

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

    Follows certain punctuation or symbols

    np_acts-logits-general · gemini-2.0-flash

    Centre Oxford, your Careers, bacterial Q, is 4

    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
    rektur
    -0.63
    indari
    -0.60
     dAtA
    -0.59
     per
    -0.57
    EndTag
    -0.56
    TRIBUTION
    -0.56
    <<(
    -0.56
    出版年
    -0.55
    cutta
    -0.55
     high
    -0.54
    POSITIVE LOGITS
    IntoConstraints
    0.71
     فريبيس
    0.66
     ujednoznacz
    0.66
    SceneManagement
    0.62
    ioutil
    0.61
     дописавши
    0.59
    RectangleBorder
    0.58
     الحره
    0.57
     useRouter
    0.55
     imprimée
    0.55
    Activations Density 0.038%

    No Known Activations