© 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. 4-GEMMASCOPE-RES-16K
    11. 11686
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to abstract mathematical structures, particularly in string theory and cohomology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ViewImports
    -0.94
    новниш
    -0.74
    adpleegd
    -0.73
     surla
    -0.73
    MemoryWarning
    -0.71
     незавершена
    -0.70
    JsonHelper
    -0.69
    Datuak
    -0.69
     PhpStorm
    -0.68
    DataAnnotations
    -0.68
    POSITIVE LOGITS
    пли
    0.45
    NgModule
    0.43
     between
    0.43
    ровку
    0.42
    naeus
    0.42
    mö
    0.40
     Walkover
    0.40
     fun
    0.40
     zug
    0.39
    Artículo
    0.39
    Activations Density 3.738%

    No Known Activations