Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 32-GEMMASCOPE-RES-131K
    6. 129881
    Prev
    Next
    INDEX
    Explanations

    concepts related to lunar cycles and their associated cultural practices

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

    moon and lunar cycles

    np_acts-logits-general · gemini-2.5-flash-lite

    numbers and time-related measurements, especially those associated with dates, lunar phases, and solar events.

    oai_token-act-pair · gpt-4.1-mini-2025-04-14Triggered by @bcywinski
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_32/width_131k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.32.hook_resid_post
    Hook Layer
    32
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mạch
    -0.36
    cstdio
    -0.35
    migrationBuilder
    -0.33
     worth
    -0.31
    todoList
    -0.31
     Robb
    -0.31
     useHistory
    -0.30
    カロ
    -0.30
    FileDescriptor
    -0.30
    glGet
    -0.29
    POSITIVE LOGITS
     moon
    2.53
     Moon
    2.25
    moon
    2.08
     MOON
    2.06
    Moon
    2.06
     moons
    1.92
     lunar
    1.90
    MOON
    1.86
     Moons
    1.75
     luna
    1.74
    Activations Density 0.062%

    No Known Activations