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. 20-GEMMASCOPE-RES-16K
    6. 11149
    Prev
    Next
    INDEX
    Explanations

    biochemical terms related to calcium, energy, and ion transport mechanisms

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

    Calcium, Ca2+, or hydrogen

    np_acts-logits-general · gemini-2.0-flash

    calcium and related elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    URLException
    -0.57
     Theſe
    -0.54
    RegressionTest
    -0.51
    ủi
    -0.50
     parkir
    -0.49
     marié
    -0.48
    cientos
    -0.48
    llary
    -0.47
     eléctricas
    -0.47
     décédé
    -0.47
    POSITIVE LOGITS
     content
    0.99
     Content
    0.82
     concentration
    0.72
     CONTENT
    0.71
    ergic
    0.69
    content
    0.69
     concentrations
    0.65
     availability
    0.64
    TextAppearance
    0.64
     contenu
    0.62
    Activations Density 1.297%

    No Known Activations