© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 13334
    Prev
    Next
    INDEX
    Explanations

    references to Yang-Mills theories and ideals in mathematical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 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
     unexpected
    -0.53
     surprising
    -0.52
     Unexpected
    -0.47
     unexpectedly
    -0.42
     matching
    -0.42
    Unexpected
    -0.41
    unexpected
    -0.39
    Matching
    -0.37
     opposite
    -0.37
    Surprisingly
    -0.37
    POSITIVE LOGITS
    Yang
    1.25
     Yang
    1.25
     YANG
    1.13
    yang
    1.05
     yang
    0.93
    ideal
    0.77
    楊
    0.76
    Ideal
    0.73
     ideal
    0.72
     Ideal
    0.69
    Activations Density 0.044%

    No Known Activations