© 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. 8-GEMMASCOPE-RES-16K
    11. 9456
    Prev
    Next
    INDEX
    Explanations

    articles or determiners in the text, particularly variations of "an" and "an"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    findpost
    -1.08
     wireType
    -0.93
     estekak
    -0.93
     propOrder
    -0.91
     literaria
    -0.89
     ffilmiau
    -0.89
    Sucesor
    -0.88
     Bly
    -0.87
     griega
    -0.87
     Goldie
    -0.86
    POSITIVE LOGITS
     an
    1.25
     An
    1.01
    An
    0.91
    cet
    0.88
    ran
    0.87
     AN
    0.87
     cet
    0.78
     anex
    0.78
    an
    0.76
    Cet
    0.75
    Activations Density 0.216%

    No Known Activations