© 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. 16118
    Prev
    Next
    INDEX
    Explanations

    technical terms and structures related to Swift and Protobuf

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

    Protobuf-related terms and "unknown" fields

    np_acts-logits-general · gemini-2.0-flash

    protobuf messages and structure

    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
    ั้ง
    -0.49
     STEP
    -0.45
    unhofer
    -0.45
     TID
    -0.43
    RRect
    -0.42
    ItemID
    -0.41
     Stirling
    -0.40
     Leibniz
    -0.39
    mlung
    -0.38
    IMIENTO
    -0.38
    POSITIVE LOGITS
    UnknownFieldSet
    0.89
    CodedInputStream
    0.84
    AccessorTable
    0.83
    sizeCache
    0.81
     ProtoMessage
    0.73
    GeneratedMessage
    0.73
    WithIOException
    0.73
    хьтан
    0.73
     protobuf
    0.71
    الحياه
    0.69
    Activations Density 0.167%

    No Known Activations