© 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
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 4702
    Prev
    Next
    INDEX
    Explanations

    variations of the word "dupe" or "duplicate"

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

    starting with "du"

    np_acts-logits-general · gemini-2.0-flash

    starts with "du"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    archiviato
    -0.33
     informes
    -0.32
    Välislingid
    -0.32
     organismos
    -0.30
     víctima
    -0.30
     biais
    -0.30
    untung
    -0.30
    Hentet
    -0.30
     coupable
    -0.29
    참고
    -0.28
    POSITIVE LOGITS
     <>",
    0.64
     dup
    0.60
    duras
    0.59
     Dup
    0.58
     Dux
    0.58
     dut
    0.57
     Duchess
    0.57
     Dub
    0.57
    rawDesc
    0.57
     dur
    0.57
    Activations Density 0.123%

    No Known Activations