© 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. 18-GEMMASCOPE-RES-16K
    11. 15715
    Prev
    Next
    INDEX
    Explanations

    different types and classifications related to coding and programming constructs

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

    Code-related terms and punctuation

    np_acts-logits-general · gemini-2.0-flash

    `query` and `getter`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DebuggerStep
    -0.67
     дописавши
    -0.61
    ForValue
    -0.61
    RegressionTest
    -0.57
     noqa
    -0.55
    <eos>
    -0.54
     AssemblyProduct
    -0.53
    IVEREF
    -0.53
    GEBURTSDATUM
    -0.52
    complexType
    -0.51
    POSITIVE LOGITS
    [
    0.75
    `,
    0.74
     &&
    0.74
     (
    0.68
    orElseThrow
    0.68
    %;
    0.68
    &
    0.67
    `{.
    0.65
    %")
    0.64
     كومونز
    0.62
    Activations Density 0.212%

    No Known Activations