© 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 EvalsExportsinterp-engineNEWAPI 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. 7223
    Prev
    Next
    INDEX
    Explanations

    financial figures and monetary amounts

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

    Numbers followed by a comma or a unit

    np_acts-logits-general · gemini-2.0-flash

    numbers like millions and billions

    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
     almost
    -0.82
    almost
    -0.74
     Almost
    -0.72
    Almost
    -0.71
     nearly
    -0.71
     مرئيه
    -0.70
     hampir
    -0.64
    nearly
    -0.64
     почти
    -0.62
     Nearly
    -0.59
    POSITIVE LOGITS
    URLException
    0.66
    extAlignment
    0.65
    JpaRepository
    0.63
     ujednoznacz
    0.59
     hundred
    0.56
    InSection
    0.56
    omock
    0.55
    NewReader
    0.53
    requireNonNull
    0.53
    íncia
    0.53
    Activations Density 0.581%

    No Known Activations