© 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. 33-GEMMASCOPE-RES-16K
    11. 11499
    Prev
    Next
    INDEX
    Explanations

    temporal markers and time-related vocabulary

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nights
    -0.57
     Night
    -0.54
     night
    -0.54
     NIGHT
    -0.51
    night
    -0.49
    nights
    -0.49
    Night
    -0.49
     Nights
    -0.46
     NUKAT
    -0.45
    NIGHT
    -0.44
    POSITIVE LOGITS
     afternoon
    1.90
    Afternoon
    1.55
     Afternoon
    1.52
    afternoon
    1.52
     afternoons
    1.37
     Nachmittag
    1.36
     pomeriggio
    1.28
    下午
    1.16
     tarde
    1.12
    午
    0.97
    Activations Density 0.178%

    No Known Activations