© 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
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 13155
    Prev
    Next
    INDEX
    Explanations

    variations of the word "mini" and phrases indicating small or compact items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    esgue
    -0.39
     écrits
    -0.35
     Juifs
    -0.33
    sibilities
    -0.32
     sommes
    -0.32
     renseignements
    -0.32
     ...
    -0.32
     szczy
    -0.32
     ..."
    -0.31
     relazioni
    -0.31
    POSITIVE LOGITS
     mini
    1.72
    Mini
    1.68
     Mini
    1.59
    mini
    1.52
     MINI
    1.39
     miniature
    1.35
    MINI
    1.32
    miniature
    1.23
     Miniature
    1.20
     мини
    1.13
    Activations Density 0.241%

    No Known Activations