© 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. 31-GEMMASCOPE-RES-16K
    11. 6130
    Prev
    Next
    INDEX
    Explanations

    references to mythology and deities from various cultures

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

    references to mythological deities and gods from various ancient cultures.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WebServlet
    -0.57
     protoimpl
    -0.57
    ðsíða
    -0.55
     NSCoder
    -0.55
    majánló
    -0.54
    izzera
    -0.52
    EndProject
    -0.52
     converge
    -0.52
    ſchaft
    -0.50
    WireFormatLite
    -0.49
    POSITIVE LOGITS
     god
    1.29
     gods
    1.26
     goddess
    1.21
     deity
    1.06
     Goddess
    1.05
     deities
    1.03
     goddesses
    1.02
    god
    1.02
    goddess
    1.00
    Goddess
    0.98
    Activations Density 0.365%

    No Known Activations