© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 102183
    Prev
    Next
    INDEX
    Explanations

    references to the term "Min" in various contexts, particularly in technical or statistical discussions

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    minTest, Min names, prefix 'Min'

    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
    Negative Logits
    URLException
    -0.55
    >{@
    -0.51
     Gegenstand
    -0.47
     męskie
    -0.46
     valoración
    -0.45
    acyjne
    -0.45
    ActionEvent
    -0.45
     fotográfico
    -0.45
    callable
    -0.43
    väg
    -0.43
    POSITIVE LOGITS
    Min
    1.94
     Min
    1.81
     MIN
    1.28
    MIN
    1.23
    getMin
    1.18
     Minnie
    1.02
     getMin
    0.97
    min
    0.95
     Mins
    0.93
     Minne
    0.90
    Activations Density 0.009%

    No Known Activations