© 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. 22-GEMMASCOPE-RES-16K
    11. 6410
    Prev
    Next
    INDEX
    Explanations

    keywords and their usage in programming or database queries

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

    SQL "query" keyword

    np_acts-logits-general · gemini-2.0-flash

    query

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LookAnd
    -0.60
    rasse
    -0.54
    INSTALLATION
    -0.53
    tvguidetime
    -0.53
    SharedCtor
    -0.52
     INSTALLATION
    -0.51
     HomeComponent
    -0.51
     localVar
    -0.51
    CodeAttribute
    -0.51
    lace
    -0.50
    POSITIVE LOGITS
     query
    3.41
    query
    3.17
     Query
    2.87
    Query
    2.75
    QUERY
    2.35
     queries
    2.32
     QUERY
    2.23
     Queries
    2.07
     querying
    2.06
     queried
    1.99
    Activations Density 0.085%

    No Known Activations