© 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. 28-GEMMASCOPE-RES-16K
    11. 5035
    Prev
    Next
    INDEX
    Explanations

    names of racers and references to racing events

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

    before commas or periods

    np_acts-logits-general · gemini-2.0-flash

    past events and times

    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
     recent
    -0.85
     yesterday
    -0.84
     ieri
    -0.83
     вчера
    -0.79
     ayer
    -0.78
     gestern
    -0.78
    Yesterday
    -0.76
     Yesterday
    -0.76
    yesterday
    -0.73
     recently
    -0.73
    POSITIVE LOGITS
     damals
    0.77
     damal
    0.70
     aquel
    0.61
     damaligen
    0.61
    当時
    0.59
    当時の
    0.58
     aquella
    0.57
    当时的
    0.56
    當時
    0.55
     terrified
    0.52
    Activations Density 0.692%

    No Known Activations