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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 7581
    Prev
    Next
    INDEX
    Explanations

    keywords related to significant rituals and celebrations in various cultural traditions

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

    Rituals, spirituality, and worship

    np_acts-logits-general · gemini-2.0-flash

    ancestor worship and rituals

    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
     consolidated
    -0.45
     Hakim
    -0.42
    skab
    -0.42
     warehousing
    -0.40
     annexed
    -0.40
     Duck
    -0.40
    lobo
    -0.40
     consolid
    -0.39
    ご覧
    -0.39
     Tarzan
    -0.39
    POSITIVE LOGITS
     ritual
    0.67
     ritu
    0.65
     symbolically
    0.64
     symbolic
    0.58
     ceremon
    0.57
    +#+#
    0.56
    Rüyada
    0.55
     simbol
    0.53
    symbolic
    0.53
    sizeCache
    0.53
    Activations Density 0.366%

    No Known Activations