Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 12545
    Prev
    Next
    INDEX
    Explanations

    references to specific days of the week, particularly Saturday

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    5
    -0.68
    Monique
    -0.65
     Ghosh
    -0.62
     Alba
    -0.60
    es
    -0.60
    MRC
    -0.59
     användas
    -0.59
     Trader
    -0.59
    lighet
    -0.58
    ५
    -0.58
    POSITIVE LOGITS
     Saturday
    2.15
     Saturdays
    2.02
    Saturday
    1.93
     saturday
    1.88
     SATURDAY
    1.75
    saturday
    1.69
    SATURDAY
    1.66
     Samstag
    1.52
    Samstag
    1.46
     Satur
    1.44
    Activations Density 0.043%

    No Known Activations