© 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 - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 29491
    Prev
    Next
    INDEX
    Explanations

    time-related references or durations

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

    durations of time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    äge
    -0.47
     chi̍t
    -0.47
    pak
    -0.44
    kins
    -0.43
    ographi
    -0.43
    ême
    -0.42
    roo
    -0.42
    cstdio
    -0.42
     wikihow
    -0.42
     Thal
    -0.41
    POSITIVE LOGITS
    WebServlet
    0.76
     écoulé
    0.69
     period
    0.68
    labelledby
    0.68
    AndroidJUnit
    0.68
     Zeitraum
    0.67
     période
    0.65
     précé
    0.65
     davor
    0.65
    Moments
    0.64
    Activations Density 0.053%

    No Known Activations