© 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. 14721
    Prev
    Next
    INDEX
    Explanations

    numeric values and measurements

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

    Numbers followed by percentages

    np_acts-logits-general · gemini-2.0-flash

    sequences of numbers after punctuation

    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
     FishBase
    -0.59
     Sixteenth
    -0.58
    Vidite
    -0.56
     Eighteenth
    -0.53
     Seventeenth
    -0.53
     Thirteenth
    -0.51
     eighteenth
    -0.50
     endwhile
    -0.49
     Fourteenth
    -0.49
    XVI
    -0.48
    POSITIVE LOGITS
    ########.
    0.74
     بيها
    0.60
    GenerationType
    0.55
    enumi
    0.54
    семь
    0.51
     الحره
    0.50
     continúas
    0.49
    :+:
    0.48
    britanni
    0.47
    ürtel
    0.47
    Activations Density 0.471%

    No Known Activations