© 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-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 5882
    Prev
    Next
    INDEX
    Explanations

    terms related to mastery or authoritative roles

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

    Appearing after the word "Master" (capitalized or lowercase)

    np_acts-logits-general · gemini-2.0-flash

    master followed by roles or systems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     suff
    -0.59
     COMMENTS
    -0.56
    alipay
    -0.52
    idends
    -0.51
     gmin
    -0.49
     Zwiebel
    -0.49
    pumpe
    -0.48
     albicans
    -0.48
     Drou
    -0.47
    ˋ
    -0.47
    POSITIVE LOGITS
     Masters
    1.33
     masters
    1.27
    Masters
    1.20
     MASTER
    1.18
    MASTER
    1.16
    masters
    1.08
     Master
    1.06
     master
    1.02
    Master
    0.98
     maîtres
    0.94
    Activations Density 0.174%

    No Known Activations