© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 4333
    Prev
    Next
    INDEX
    Explanations

    phrases detailing common usage, characteristics, and behaviors of various products or methods

    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
     Paglinawan
    -0.61
    Sklici
    -0.56
     supuestamente
    -0.56
    確かに
    -0.55
     conceivably
    -0.54
     allegedly
    -0.54
     poffible
    -0.53
     lenker
    -0.52
    いいのか
    -0.52
    Населення
    -0.51
    POSITIVE LOGITS
     suele
    0.76
     usually
    0.69
     Generally
    0.67
    meist
    0.66
    Generally
    0.65
     either
    0.65
     generally
    0.64
     suelen
    0.64
     Usually
    0.63
    Usually
    0.62
    Activations Density 0.456%

    No Known Activations