© 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. 921
    Prev
    Next
    INDEX
    Explanations

    elements of a database table definition

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

    SQL code and table definitions

    np_acts-logits-general · gemini-2.0-flash

    SQL column definitions and 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
    Not in Any Lists

    No Comments

    Negative Logits
     XM
    -0.44
    expandindo
    -0.43
    กรณ์
    -0.43
     StatelessWidget
    -0.41
    Nassau
    -0.41
     Pera
    -0.40
     createState
    -0.40
     despe
    -0.39
     plásticos
    -0.39
    וות
    -0.39
    POSITIVE LOGITS
    ########.
    0.81
     <=",
    0.79
    simpleType
    0.62
     column
    0.58
    はじめに
    0.58
    Column
    0.58
     Column
    0.58
     COLUMN
    0.57
     propOrder
    0.57
    Datuak
    0.56
    Activations Density 0.124%

    No Known Activations