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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 2687
    Prev
    Next
    INDEX
    Explanations

    specific time references related to events or schedules

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

    Time or location words

    np_acts-logits-general · gemini-2.0-flash

    events at or around times

    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
    RegressionTest
    -0.70
    Days
    -0.67
     Days
    -0.66
    niosek
    -0.62
     DAYS
    -0.58
     days
    -0.56
    几天
    -0.56
     weekends
    -0.56
    days
    -0.55
     días
    -0.55
    POSITIVE LOGITS
     around
    1.52
     Around
    1.35
    Around
    1.32
    around
    1.28
     sekitar
    1.20
     AROUND
    1.15
     intorno
    1.11
     alrededor
    1.07
    AROUND
    0.97
     attorno
    0.88
    Activations Density 0.147%

    No Known Activations