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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 2398
    Prev
    Next
    INDEX
    Explanations

    keywords related to astronomical events, specifically solar and lunar eclipses

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

    Lunar phases and eclipses

    np_acts-logits-general · gemini-2.0-flash

    full moon and eclipses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ResumeLayout
    -0.59
    InSection
    -0.57
    Codes
    -0.52
    बाह
    -0.51
     getModel
    -0.51
     scalp
    -0.50
    Vital
    -0.50
    Explor
    -0.48
     solenoid
    -0.47
    ements
    -0.47
    POSITIVE LOGITS
     Full
    0.81
     phases
    0.78
     waxing
    0.77
     crescent
    0.77
     eclipse
    0.73
     phase
    0.73
     waning
    0.72
    Full
    0.71
    eclipse
    0.71
    Phases
    0.69
    Activations Density 0.174%

    No Known Activations