© 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. 28-GEMMASCOPE-RES-16K
    6. 7443
    Prev
    Next
    INDEX
    Explanations

    terms and references related to historical dynasties and monarchies

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

    kings, queens, and ruling

    np_acts-logits-general · gemini-2.0-flash

    ruling over Denmark, Schleswig, Sweden

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sensei
    -0.60
     Ovid
    -0.58
     sensei
    -0.55
     Parac
    -0.51
     Phry
    -0.50
     Philist
    -0.49
     Apu
    -0.49
     Pythag
    -0.48
     Hippo
    -0.48
     Philo
    -0.48
    POSITIVE LOGITS
     throne
    0.79
     ruler
    0.71
     trono
    0.69
     coronation
    0.67
     gobern
    0.66
     rulers
    0.65
     ruling
    0.62
     monarchs
    0.62
     pemerintahan
    0.62
     règne
    0.62
    Activations Density 0.701%

    No Known Activations