© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 54377
    Prev
    Next
    INDEX
    Explanations

    SQL commands and syntax related to altering and updating database tables

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

    ALTER TABLE and UPDATE statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.56
     оригіналу
    -0.50
    CloseOperation
    -0.47
     useAppContext
    -0.44
     faſt
    -0.43
    featureID
    -0.43
     Chwiliwch
    -0.42
     sukker
    -0.42
    SPJ
    -0.41
    Gön
    -0.41
    POSITIVE LOGITS
    ALTER
    0.66
    setAccessible
    0.58
    HttpPut
    0.57
    AlterField
    0.56
    updateOne
    0.54
    findOneAndUpdate
    0.51
    AndUpdate
    0.49
    ToUpdate
    0.48
    PutMapping
    0.47
     update
    0.47
    Activations Density 0.027%

    No Known Activations