© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 34-GEMMASCOPE-RES-16K
    11. 11481
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to time, events, and actions occurring within contexts of scheduling or timelines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    apunov
    -0.48
     TextInputType
    -0.45
    Читати
    -0.40
     Roskov
    -0.40
     calendriers
    -0.39
    ✨:
    -0.36
    LoggerFactory
    -0.36
    artney
    -0.35
    balleur
    -0.35
    findpost
    -0.35
    POSITIVE LOGITS
     time
    3.78
    time
    2.55
     tijd
    2.47
     tiempo
    2.19
    Time
    2.14
     Time
    2.14
     waktu
    2.06
    时间
    2.03
     TIME
    2.02
     время
    1.99
    Activations Density 1.128%

    No Known Activations