© 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. 8128
    Prev
    Next
    INDEX
    Explanations

    SQL queries related to aggregating and filtering data from database tables

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

    SQL "select" or "group by" statements

    np_acts-logits-general · gemini-2.0-flash

    sql select statements

    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
    DeleteBehavior
    -0.89
    KommentareTeilen
    -0.82
    HtmlAttribute
    -0.81
    SequentialGroup
    -0.79
    存于互联网档案馆
    -0.76
     MonoBehaviour
    -0.74
     isKindOfClass
    -0.69
    UnusedPrivate
    -0.68
    Diwedd
    -0.68
     ujednoznacz
    -0.67
    POSITIVE LOGITS
     select
    0.60
     calendriers
    0.47
    select
    0.46
    quellen
    0.45
     limit
    0.42
     limited
    0.42
     group
    0.42
     --
    0.42
    SELECT
    0.40
    ÓW
    0.39
    Activations Density 0.395%

    No Known Activations