© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 15506
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Thursday" and related dates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    4
    -0.73
    Brend
    -0.69
    iyle
    -0.64
     nonatomic
    -0.63
     Brend
    -0.62
    ỡng
    -0.62
     pitié
    -0.62
     Surely
    -0.62
    ApplicationTests
    -0.61
    9
    -0.60
    POSITIVE LOGITS
     Thursday
    1.68
    Thursday
    1.66
     Wednesday
    1.61
     Friday
    1.53
    Wednesday
    1.53
    Friday
    1.46
     Thursdays
    1.40
     Fridays
    1.34
     THURSDAY
    1.32
     Tuesday
    1.30
    Activations Density 0.065%

    No Known Activations