© 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. 22-GEMMASCOPE-RES-16K
    11. 4355
    Prev
    Next
    INDEX
    Explanations

    references to demands for custom product manufacturing and specifications

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

    that follow certain modal verbs/nouns

    np_acts-logits-general · gemini-2.0-flash

    Indonesian currency and related descriptions

    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
     boroughs
    -0.73
    etcode
    -0.72
     hatchet
    -0.68
    <>());
    -0.67
    etCode
    -0.67
    kaŭ
    -0.64
    blumen
    -0.63
     hierogly
    -0.62
     disambiguazione
    -0.62
     tewas
    -0.62
    POSITIVE LOGITS
     Indonesia
    0.65
    TagMode
    0.64
     Indonesian
    0.62
     lont
    0.51
     akad
    0.50
     dan
    0.49
     meng
    0.48
     Rp
    0.47
    Indonesia
    0.46
    returnType
    0.45
    Activations Density 0.049%

    No Known Activations