© 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 EvalsExportsAPI 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. 8838
    Prev
    Next
    INDEX
    Explanations

    references to spiritual practices and their implications on self-control and morality

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

    associated with evil or negativity

    np_acts-logits-general · gemini-2.0-flash

    sinful and evil concepts

    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

    No Comments

    Negative Logits
     vérité
    -0.54
    complexContent
    -0.51
    ритори
    -0.48
    ückt
    -0.48
    grana
    -0.48
    brü
    -0.47
    arques
    -0.46
    OrEqualTo
    -0.46
     Wunder
    -0.44
    onComplete
    -0.44
    POSITIVE LOGITS
     devil
    0.98
     evil
    0.96
     worldly
    0.93
     Satan
    0.92
    Satan
    0.91
     demonic
    0.87
     sinful
    0.85
    evil
    0.85
     Devil
    0.85
     satan
    0.82
    Activations Density 0.238%

    No Known Activations