© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 7004
    Prev
    Next
    INDEX
    Explanations

    phrases containing "half."

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

    "half" followed by a unit of time or quantity

    np_acts-logits-general · gemini-2.0-flash

    half a

    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
    optString
    -0.59
     InputDecoration
    -0.57
     StatefulWidget
    -0.57
     scolaires
    -0.53
    Становништво
    -0.53
     AssemblyProduct
    -0.52
     Meksiku
    -0.51
     dedans
    -0.51
    diferentes
    -0.50
    expandindo
    -0.50
    POSITIVE LOGITS
     dozen
    0.84
    heartedly
    0.77
    moon
    0.71
    way
    0.69
     hour
    0.68
     moon
    0.67
     way
    0.66
     hearted
    0.66
    penny
    0.66
    hearted
    0.65
    Activations Density 0.110%

    No Known Activations