© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 5693
    Prev
    Next
    INDEX
    Explanations

    elements related to magic and supernatural themes

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

    words and themes related to magic, supernatural powers, and mystical phenomena.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nahilalakip
    -0.59
    ypep
    -0.53
     benchmark
    -0.53
    retweeted
    -0.50
    issons
    -0.49
     Benchmark
    -0.49
     Tuber
    -0.48
    komen
    -0.48
     Incon
    -0.48
     herren
    -0.47
    POSITIVE LOGITS
     magic
    0.85
     witchcraft
    0.84
     magia
    0.77
     spells
    0.77
     sorcery
    0.75
    magic
    0.73
     sorcerer
    0.72
     mág
    0.72
     spell
    0.72
     magical
    0.71
    Activations Density 0.159%

    No Known Activations