© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 7580
    Prev
    Next
    INDEX
    Explanations

    references to temporal events and significant days

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    something is about to happen

    np_acts-logits-general · gemini-2.0-flash

    impending future events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    Rüyada
    -0.47
     Picchu
    -0.41
    Géographie
    -0.39
    !*\
    -0.39
    ONAUT
    -0.38
    verwijspagina
    -0.37
     estekak
    -0.35
    TypedDataSet
    -0.35
     ComVisible
    -0.34
    enderror
    -0.33
    POSITIVE LOGITS
     approaching
    1.78
     imminent
    1.58
     nearing
    1.49
     impending
    1.48
     soon
    1.41
     upcoming
    1.34
     looming
    1.31
    即将
    1.29
    soon
    1.25
     sắp
    1.22
    Activations Density 0.361%

    No Known Activations