© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 86484
    Prev
    Next
    INDEX
    Explanations

    references to the moon in various contexts

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

    moon glow

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    Not in Any Lists

    No Comments

    Negative Logits
    seteq
    -0.45
    ftagPool
    -0.45
    TagHelpers
    -0.41
    CLUDING
    -0.38
     Tư
    -0.38
     פרי
    -0.37
     للمعارف
    -0.35
    jší
    -0.34
     tư
    -0.34
    Daryl
    -0.34
    POSITIVE LOGITS
     Moon
    1.29
     MOON
    1.28
    Moon
    1.26
     moon
    1.23
    moon
    1.17
    MOON
    1.09
    Moons
    0.99
     Moons
    0.98
     moonlight
    0.96
    moons
    0.91
    Activations Density 0.009%

    No Known Activations