© 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. 21-GEMMASCOPE-RES-16K
    11. 5264
    Prev
    Next
    INDEX
    Explanations

    time-related phrases or specific durations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    minute
    -0.80
     minute
    -0.76
     hour
    -0.75
     minutes
    -0.72
     hours
    -0.72
     minutos
    -0.71
     HOUR
    -0.70
    hour
    -0.70
    Minute
    -0.70
     Minuten
    -0.68
    POSITIVE LOGITS
     seconds
    0.74
     milliseconds
    0.71
    hoeddwyd
    0.65
     AssemblyCompany
    0.64
     split
    0.63
     Sec
    0.62
    msec
    0.62
     ſec
    0.60
     msec
    0.59
     ms
    0.59
    Activations Density 0.311%

    No Known Activations