© 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. 8171
    Prev
    Next
    INDEX
    Explanations

    code snippets related to NumPy and array manipulation

    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
     تضيفلها
    -0.69
    findOrFail
    -0.60
    EnableWeb
    -0.60
     Dresden
    -0.58
     NDL
    -0.58
    Kund
    -0.56
    odeon
    -0.56
    abilirsiniz
    -0.55
    Trả
    -0.55
    DrawerToggle
    -0.55
    POSITIVE LOGITS
     np
    1.13
    np
    0.94
     numpy
    0.85
    asarray
    0.80
     NPs
    0.77
    umpy
    0.74
     ModelExpression
    0.71
     NPY
    0.71
     NP
    0.70
    ostante
    0.70
    Activations Density 0.038%

    No Known Activations