© 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-2-9B
    7. Residual Stream - 16k
    9. 38-GEMMASCOPE-RES-16K
    11. 9434
    Prev
    Next
    INDEX
    Explanations

    concepts related to mathematical structures and properties, particularly in the context of theoretical physics or advanced mathematics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    interopRequire
    -0.65
     للمعارف
    -0.59
     utafitiHapana
    -0.55
    ImageContext
    -0.53
    раздо
    -0.52
     invokingState
    -0.51
    IContainer
    -0.49
    ällor
    -0.49
    profen
    -0.48
     otomatig
    -0.48
    POSITIVE LOGITS
     i
    2.02
     ie
    1.95
     cioè
    1.70
     namely
    1.70
     یعنی
    1.60
     czyli
    1.55
     yaitu
    1.52
    即
    1.50
    つまり
    1.47
    すな
    1.47
    Activations Density 1.559%

    No Known Activations