© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 9241
    Prev
    Next
    INDEX
    Explanations

    technical terms and elements related to programming or network protocols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     MacGregor
    -0.70
    danny
    -0.65
    tria
    -0.65
    ugal
    -0.62
     Dwyer
    -0.59
    chalten
    -0.59
     Griffith
    -0.58
    quial
    -0.58
    βά
    -0.57
     Kristen
    -0.57
    POSITIVE LOGITS
    itemize
    3.90
    displayquote
    1.66
    enumerate
    1.33
    CJK
    1.22
    awtextra
    0.98
     kasarigan
    0.85
    AccessorTable
    0.85
    WithFormat
    0.83
    tabular
    0.82
    DispatchToProps
    0.82
    Activations Density 0.017%

    No Known Activations