© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 106977
    Prev
    Next
    INDEX
    Explanations

    references to symmetric groups and symmetric functions in mathematical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    symmetric group

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ://
    -0.38
    :///
    -0.38
    Pul
    -0.38
     Pul
    -0.37
    \.
    -0.37
     fossa
    -0.36
     getFile
    -0.36
    He
    -0.36
    KF
    -0.35
     Kuli
    -0.35
    POSITIVE LOGITS
     symmetric
    2.50
     Symmetric
    2.41
    Symmetric
    2.30
    symmetric
    2.17
     symmetrical
    1.91
    ymmetric
    1.61
     asymmetric
    1.51
     Asymmetric
    1.43
     symmetry
    1.22
     asymmetrical
    1.20
    Activations Density 0.017%

    No Known Activations