© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 12427
    Prev
    Next
    INDEX
    Explanations

    the occurrence of the word "de" in various contexts

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

    "de"

    np_acts-logits-general · gemini-2.0-flash

    prepositions or contractions

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
     chrétien
    -0.71
     nôtre
    -0.61
     raiſ
    -0.61
     ainfi
    -0.55
     chré
    -0.54
     Jesucristo
    -0.54
     slutt
    -0.53
     Lainnya
    -0.53
     ſta
    -0.52
     vôtre
    -0.52
    POSITIVE LOGITS
     de
    1.07
     of
    0.94
     De
    0.85
     OF
    0.84
    lof
    0.80
    bde
    0.80
    De
    0.78
     DE
    0.77
    ของ
    0.75
     di
    0.75
    Activations Density 0.035%

    No Known Activations