© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 9990
    Prev
    Next
    INDEX
    Explanations

    references to the French article "De" in legal or formal documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     itſelf
    -0.87
     Efq
    -0.84
    StoryboardSegue
    -0.83
     Chriſt
    -0.80
     faſt
    -0.80
     Houſe
    -0.79
     Majefty
    -0.77
     ―――――
    -0.77
     leaſt
    -0.76
     ſhall
    -0.74
    POSITIVE LOGITS
     De
    2.37
    De
    2.13
     DeWitt
    1.04
     DeV
    1.01
     Де
    0.96
     Di
    0.92
     detachment
    0.91
     DeL
    0.90
    defer
    0.88
     deoxy
    0.84
    Activations Density 0.093%

    No Known Activations