© 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. 15-GEMMASCOPE-RES-16K
    11. 5660
    Prev
    Next
    INDEX
    Explanations

    references to simulations and studies conducted in scientific research

    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
    GEBURTSDATUM
    -1.27
    Personensuche
    -1.08
    parsedMessage
    -1.05
    SharedDtor
    -1.01
    InstrumentedTest
    -0.98
     дописавши
    -0.97
    ConstraintMaker
    -0.95
     /\.
    -0.92
     שוליים
    -0.89
    tagext
    -0.89
    POSITIVE LOGITS
    bila
    0.46
     
    0.46
     هنگ
    0.43
    ̣t
    0.42
     absolutely
    0.42
     ül
    0.42
    stav
    0.41
    lamo
    0.41
     most
    0.39
    هنگ
    0.38
    Activations Density 0.948%

    No Known Activations