© 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. 2-GEMMASCOPE-RES-16K
    11. 2982
    Prev
    Next
    INDEX
    Explanations

    mathematical terms and symbols, particularly those related to equations and expressions in physics

    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
     للمعارف
    -1.30
     resourceCulture
    -1.20
     doInBackground
    -1.15
     ComVisible
    -1.11
    IsContent
    -1.09
    ViewImports
    -1.05
    adaptiveStyles
    -1.02
     StatefulWidget
    -1.01
    migrationBuilder
    -0.99
     समीक्षाओं
    -0.99
    POSITIVE LOGITS
    i
    0.51
     i
    0.49
     ±
    0.47
    ∓
    0.45
    <eos>
    0.45
     j
    0.44
     par
    0.42
     n
    0.42
    /
    0.40
     et
    0.39
    Activations Density 1.775%

    No Known Activations