© 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-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 304
    Prev
    Next
    INDEX
    Explanations

    concepts related to spiritual and mystical experiences

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

    Spiritual and energy-related concepts

    np_acts-logits-general · gemini-2.0-flash

    chakra

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    •moral_agent
    •jailbreak_evil_confidant

    No Comments

    Negative Logits
    NameInMap
    -0.76
     ujednoznacz
    -0.75
     Numerade
    -0.65
     referenties
    -0.64
    تقاوى
    -0.63
    ItemBackground
    -0.61
    밌
    -0.60
    //
    -0.60
     Asympto
    -0.59
    addGap
    -0.59
    POSITIVE LOGITS
     spiritual
    0.91
     chakras
    0.91
     chakra
    0.89
     energies
    0.89
     energy
    0.85
     spiritually
    0.81
     Feng
    0.79
     feng
    0.78
     psychic
    0.78
     auras
    0.76
    Activations Density 0.161%

    No Known Activations