© 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-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 3618
    Prev
    Next
    INDEX
    Explanations

    references to the moon and lunar themes

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

    words and concepts related to the moon, including lunar terminology and moonlight.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    the word "moon" and related lunar imagery or concepts.

    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
     compromis
    -0.35
     opérateur
    -0.35
    Atsauces
    -0.33
     lagi
    -0.33
     tapis
    -0.33
    โท
    -0.32
     AssemblyCulture
    -0.32
    localctx
    -0.32
    endpush
    -0.32
     intptr
    -0.32
    POSITIVE LOGITS
     lunar
    1.09
     Moon
    1.05
     moon
    1.03
     Lunar
    0.99
    Moon
    0.95
     MOON
    0.94
    Lunar
    0.90
    lunar
    0.90
     moonlight
    0.90
     Moonlight
    0.88
    Activations Density 0.097%

    No Known Activations