© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 4999
    Prev
    Next
    INDEX
    Explanations

    mathematical notations and symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    "
    -0.55
    _
    -0.54
    rad
    -0.50
    ut
    -0.44
    腊
    -0.43
    ql
    -0.43
    *
    -0.43
    <h2>
    -0.43
    ud
    -0.43
    ">
    -0.42
    POSITIVE LOGITS
    \{\\
    1.22
     للاسماء
    1.05
     nahilalakip
    1.04
     estimés
    1.04
    RenderAtEndOf
    1.00
     Савезне
    0.99
     BoxFit
    0.97
     pinulongan
    0.96
    AccessorTable
    0.95
     InputDecoration
    0.93
    Activations Density 0.160%

    No Known Activations