© 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. 3334
    Prev
    Next
    INDEX
    Explanations

    specific SQL table structures and definitions, including fields and data types

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

    SQL data types after column names

    np_acts-logits-general · gemini-2.0-flash

    SQL data types and fields

    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
    •SQL-labeled features

    No Comments

    Negative Logits
     propOrder
    -0.77
    enumii
    -0.67
    enumi
    -0.58
     الرياضيه
    -0.57
    Tembelea
    -0.55
    RTLD
    -0.54
    BagConstraints
    -0.54
    WireFormatLite
    -0.53
     lenker
    -0.53
     ControllerBase
    -0.52
    POSITIVE LOGITS
     متعلقه
    0.71
     blob
    0.61
     binary
    0.56
    blob
    0.54
    BLO
    0.53
     blobs
    0.51
    igshid
    0.51
    binary
    0.49
     texted
    0.47
    NV
    0.46
    Activations Density 0.405%

    No Known Activations