© 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. 2-GEMMASCOPE-RES-16K
    11. 8317
    Prev
    Next
    INDEX
    Explanations

    characters or symbols from non-Latin scripts, particularly focusing on their frequency and arrangement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     PENS
    -0.71
    ########.
    -0.63
     Italijani
    -0.60
     DETERMIN
    -0.59
    okovic
    -0.59
     թվ
    -0.56
     sorte
    -0.56
    ё
    -0.56
     FIL
    -0.55
     sou
    -0.54
    POSITIVE LOGITS
     BorderRadius
    0.89
    Ārējās
    0.73
    அ
    0.67
    theilung
    0.67
    Czytaj
    0.66
    இ
    0.65
     അ
    0.64
     მ
    0.63
     MainAxisSize
    0.62
    polation
    0.62
    Activations Density 0.011%

    No Known Activations