© 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. 14-GEMMASCOPE-RES-16K
    11. 14734
    Prev
    Next
    INDEX
    Explanations

    technical terminology and structural elements present in digital documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    最快更新
    -0.97
     Wickham
    -0.88
    MessageState
    -0.78
     HasFactory
    -0.76
     Paglinawan
    -0.74
    brate
    -0.74
    Boulder
    -0.73
     unknownFields
    -0.73
     fieldNum
    -0.73
    iconque
    -0.72
    POSITIVE LOGITS
    <h3>
    0.86
    <h2>
    0.80
    <table>
    0.78
    <h4>
    0.77
    <h5>
    0.76
    <h6>
    0.75
    subsubsection
    0.74
    subsection
    0.69
    <h1>
    0.67
    multirow
    0.65
    Activations Density 0.040%

    No Known Activations