© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 3802
    Prev
    Next
    INDEX
    Explanations

    phrases and concepts related to ritual offerings and sacrifices

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

    references to ritual offerings and sacrifices made to deities or divine beings.

    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
     menyus
    -0.39
     armadura
    -0.37
     coached
    -0.36
     coach
    -0.35
    outé
    -0.35
    aqu
    -0.34
     AQU
    -0.34
    ございます
    -0.34
     aqu
    -0.34
    SizeF
    -0.34
    POSITIVE LOGITS
     worship
    1.18
     shrine
    1.09
     temple
    1.08
     sacrifices
    1.00
     altar
    1.00
     worshipping
    0.98
     sacrifice
    0.98
     Temple
    0.96
     Worship
    0.94
    worship
    0.93
    Activations Density 0.216%

    No Known Activations