© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 13974
    Prev
    Next
    INDEX
    Explanations

    mentions of ceremonies and formal events

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

    "ceremony" or its variants

    np_acts-logits-general · gemini-2.0-flash

    Hindu ceremony

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     inconsciente
    -0.35
     nabíz
    -0.34
     campion
    -0.32
     enquête
    -0.32
     consulter
    -0.31
     houſe
    -0.31
     prostitu
    -0.31
     ums
    -0.31
    frequent
    -0.30
    relser
    -0.30
    POSITIVE LOGITS
     ceremony
    1.77
     ceremon
    1.49
     ceremonies
    1.47
     Ceremony
    1.46
     ceremonial
    1.39
     ceremonia
    1.36
     Ceremon
    1.32
     Ceremonies
    1.26
     cerimonia
    1.26
     cérémonie
    1.23
    Activations Density 0.264%

    No Known Activations