© 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 EvalsExportsinterp-engineNEWAPI 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. 3357
    Prev
    Next
    INDEX
    Explanations

    elements related to religious rituals or ceremonies

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

    religious and liturgical language related to Catholic Mass and worship services.

    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
    rašymas
    -0.46
    tvguidetime
    -0.45
    出版年
    -0.45
    Personendaten
    -0.44
    GEBURTS
    -0.44
     bambú
    -0.42
     maternidade
    -0.42
    Birth
    -0.42
     stork
    -0.42
    Биография
    -0.41
    POSITIVE LOGITS
     readings
    0.68
     Readings
    0.62
    Readings
    0.58
     reading
    0.57
     Mass
    0.51
    AsUp
    0.48
    reading
    0.45
     Reading
    0.45
     read
    0.44
     lectura
    0.44
    Activations Density 0.125%

    No Known Activations