© 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. 21-GEMMASCOPE-RES-16K
    11. 16123
    Prev
    Next
    INDEX
    Explanations

    temporal references related to dates and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 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
     July
    -0.70
    JULY
    -0.69
    July
    -0.67
     JULY
    -0.64
    july
    -0.62
     Midsummer
    -0.60
    七月
    -0.60
     June
    -0.60
     summer
    -0.59
    SUMMER
    -0.59
    POSITIVE LOGITS
     January
    0.70
    Winter
    0.69
    January
    0.69
     Winter
    0.69
     winter
    0.69
     invern
    0.63
     WINTER
    0.63
    winter
    0.59
    February
    0.57
     wintry
    0.56
    Activations Density 0.502%

    No Known Activations