© 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. 4-GEMMASCOPE-RES-16K
    11. 10557
    Prev
    Next
    INDEX
    Explanations

    references to the "fmt" package in Go programming language code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    半
    -0.62
    modelBuilder
    -0.61
    antası
    -0.56
    nor
    -0.53
    <eos>
    -0.52
    धि
    -0.50
     Mor
    -0.49
     half
    -0.49
     semi
    -0.48
    coff
    -0.47
    POSITIVE LOGITS
    fmt
    3.03
     fmt
    2.70
    Fmt
    1.31
    FMT
    1.18
    RenderAtEndOf
    0.93
     propOrder
    0.84
    testify
    0.84
     XCTest
    0.83
     reaſon
    0.82
     Efq
    0.78
    Activations Density 0.048%

    No Known Activations