© 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. 1-GEMMASCOPE-RES-16K
    11. 2903
    Prev
    Next
    INDEX
    Explanations

    references to years and months

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CRITICAL
    -0.37
    IFICATE
    -0.36
     Bick
    -0.36
    IBAction
    -0.35
     Schmitt
    -0.34
    dib
    -0.34
    tructive
    -0.34
    atelli
    -0.34
    cating
    -0.34
    keletal
    -0.34
    POSITIVE LOGITS
     year
    3.38
    Year
    3.03
     Year
    3.02
     YEAR
    2.88
    year
    2.86
     año
    2.84
    YEAR
    2.77
     année
    2.63
     tahun
    2.56
     jaar
    2.39
    Activations Density 0.169%

    No Known Activations