© 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. 14-GEMMASCOPE-RES-16K
    11. 5445
    Prev
    Next
    INDEX
    Explanations

    terms and phrases that indicate types, categories, or classifications of items or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IntoConstraints
    -0.77
    ScopeManager
    -0.71
    makeConstraints
    -0.66
    出版年
    -0.62
     raiſ
    -0.62
     fubject
    -0.61
    webElement
    -0.61
    DotNetBar
    -0.61
    Personendaten
    -0.61
     cauſe
    -0.60
    POSITIVE LOGITS
     sorta
    0.90
     quasi
    0.75
     sort
    0.75
     jakby
    0.70
     pseudo
    0.69
     sortes
    0.68
    kinda
    0.68
    というか
    0.68
     kind
    0.67
     like
    0.66
    Activations Density 0.250%

    No Known Activations