© 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-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 9412
    Prev
    Next
    INDEX
    Explanations

    phrases related to time and duration, particularly in relation to events and experiences

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

    time periods

    np_acts-logits-general · gemini-2.0-flash

    time periods like years

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     generations
    -0.61
     centuries
    -0.58
     century
    -0.57
    century
    -0.55
    GEBURTSDATUM
    -0.54
     decades
    -0.54
     legends
    -0.53
    generation
    -0.52
     CENTURY
    -0.51
     قرن
    -0.50
    POSITIVE LOGITS
    三年
    0.89
    两年
    0.84
     year
    0.78
    一年
    0.76
     Year
    0.68
    去年
    0.68
    二年
    0.64
    四年
    0.63
    Year
    0.60
    半年
    0.58
    Activations Density 0.492%

    No Known Activations