© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 34-GEMMASCOPE-RES-16K
    11. 10470
    Prev
    Next
    INDEX
    Explanations

    references to titles and names that include the term "du" or related variants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vė
    -0.31
    انيف
    -0.31
    ценка
    -0.29
     niebla
    -0.28
    RequestBody
    -0.28
     دیکھیے
    -0.28
     drapeau
    -0.27
     malheur
    -0.27
    ➩
    -0.26
     aho
    -0.26
    POSITIVE LOGITS
     Du
    0.77
    Du
    0.75
     DU
    0.65
    OGND
    0.64
     du
    0.63
     nakalista
    0.63
    du
    0.61
     AssemblyVersion
    0.61
     Duf
    0.59
     Dup
    0.59
    Activations Density 0.154%

    No Known Activations