© 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. 20-GEMMASCOPE-RES-16K
    11. 911
    Prev
    Next
    INDEX
    Explanations

    various types of definitions and categorizations in a text

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

    Code or mathematical expressions

    np_acts-logits-general · gemini-2.0-flash

    mathematical and technical terms

    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
     sulfur
    -0.68
     Society
    -0.68
    Society
    -0.66
     SOCIETY
    -0.66
     sulfate
    -0.66
     society
    -0.65
     Sociedade
    -0.64
     sư
    -0.64
     serine
    -0.62
     Senate
    -0.62
    POSITIVE LOGITS
    MigrationBuilder
    0.72
    Personensuche
    0.66
    NewReader
    0.63
     Winaray
    0.58
    DrawerToggle
    0.57
     Biôgrafia
    0.57
    ↹
    0.56
     <=",
    0.56
    kuuta
    0.54
    errHandler
    0.54
    Activations Density 0.540%

    No Known Activations