© 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. 16-GEMMASCOPE-RES-16K
    11. 11525
    Prev
    Next
    INDEX
    Explanations

    queries related to database aggregation functions

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

    SQL or code "group by" operations

    np_acts-logits-general · gemini-2.0-flash

    group by and aggregate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rungsseite
    -0.54
    ateral
    -0.54
     internazionali
    -0.50
    WindowConstants
    -0.49
    oxin
    -0.46
    ometal
    -0.46
     downgrade
    -0.45
     velho
    -0.43
     downg
    -0.43
    комплек
    -0.43
    POSITIVE LOGITS
     AssemblyCulture
    0.81
     COUNT
    0.69
     Count
    0.67
    stridium
    0.65
    lichung
    0.63
    lapsingToolbar
    0.63
     count
    0.63
     EconPapers
    0.62
     uniques
    0.61
    groupby
    0.61
    Activations Density 0.693%

    No Known Activations