© 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. 20-GEMMASCOPE-RES-16K
    11. 3540
    Prev
    Next
    INDEX
    Explanations

    SQL query structures and associated syntax elements

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

    SQL "WHERE" clause

    np_acts-logits-general · gemini-2.0-flash

    WHERE clauses in queries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •SQL-labeled features

    No Comments

    Negative Logits
    VersionUID
    -0.58
     MainAxisSize
    -0.55
    <_>
    -0.54
    ẫu
    -0.54
     itſelf
    -0.53
    TotalCount
    -0.53
     counts
    -0.53
    StructEnd
    -0.52
     defStyle
    -0.52
     Toda
    -0.52
    POSITIVE LOGITS
    Portail
    0.67
    eqn
    0.64
    PageRoute
    0.64
    addCriterion
    0.60
    setVerticalGroup
    0.59
     aikaa
    0.59
    olge
    0.58
    HasForeignKey
    0.57
    EndContext
    0.57
    Kaynakça
    0.56
    Activations Density 0.076%

    No Known Activations