© 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. MLP Out - 131k
    9. 6-GEMMASCOPE-MLP-131K
    11. 108681
    Prev
    Next
    INDEX
    Explanations

    references to the term "Mint" in various contexts, particularly related to software or flavor

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-mlp/layer_6/width_131k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.6.hook_mlp_out
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mint
    -2.03
     Mint
    -2.00
    Mint
    -1.79
    mint
    -1.65
     MINT
    -1.59
     peppermint
    -0.91
     minted
    -0.86
     Peppermint
    -0.74
     menthe
    -0.72
    amint
    -0.67
    POSITIVE LOGITS
    CppMethod
    0.49
     يتيمه
    0.38
    ãng
    0.35
     Olimpia
    0.33
    ۗ
    0.32
    Stein
    0.31
    Season
    0.31
    ogramm
    0.30
     خارجية
    0.30
     Philist
    0.30
    Activations Density 0.000%

    No Known Activations