© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 11737
    Prev
    Next
    INDEX
    Explanations

    the article "An" used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     estekak
    -0.94
    findpost
    -0.91
     propOrder
    -0.87
     wireType
    -0.84
    出版年
    -0.82
     preocupes
    -0.82
     ffilmiau
    -0.81
     ModelExpression
    -0.81
     griega
    -0.81
    webElementXpaths
    -0.81
    POSITIVE LOGITS
     an
    0.88
    ran
    0.80
     An
    0.77
    cet
    0.76
     AN
    0.72
    nt
    0.69
     Anwar
    0.68
     cet
    0.67
    An
    0.67
     "}";
    0.67
    Activations Density 0.212%

    No Known Activations