© 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. 3677
    Prev
    Next
    INDEX
    Explanations

    references to data structures or code elements in programming

    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
     NDEBUG
    -0.68
    ruptedException
    -0.65
    DrawerToggle
    -0.64
     TextInputType
    -0.60
     Utama
    -0.59
    بوابة
    -0.56
    setupUi
    -0.53
    ชี
    -0.53
    ViewInit
    -0.53
    idemia
    -0.52
    POSITIVE LOGITS
    addPreferredGap
    0.80
     تضيفلها
    0.71
    yszer
    0.69
    gunt
    0.64
    esez
    0.60
     Arie
    0.60
    ValueStyle
    0.60
    GEBURTSDATUM
    0.60
     Dés
    0.59
    WriteAttribute
    0.59
    Activations Density 0.056%

    No Known Activations