© 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. 18-GEMMASCOPE-RES-16K
    11. 2123
    Prev
    Next
    INDEX
    Explanations

    specific grammatical forms and keywords related to statistical or scientific analysis

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

    ending with "scripts"

    np_acts-logits-general · gemini-2.0-flash

    word beginnings and endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Vidite
    -1.18
    WebElementEntity
    -1.14
     Италијани
    -1.07
    Hauptartikel
    -1.05
    WebVitals
    -1.04
     Meksiku
    -1.03
     nahilalakip
    -1.03
    DoubleQuotes
    -0.95
     kaarangay
    -0.95
     EconPapers
    -0.95
    POSITIVE LOGITS
    entibus
    0.66
     \
    0.50
    ثة
    0.47
    less
    0.43
     lää
    0.43
    って言
    0.42
     löyty
    0.42
     näky
    0.41
     kiin
    0.41
     M
    0.41
    Activations Density 0.485%

    No Known Activations