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-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 15117
    Prev
    Next
    INDEX
    Explanations

    references to the current day or present time

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

    "today"

    np_acts-logits-general · gemini-2.0-flash

    current day or 'today's'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ionario
    -0.42
    ínű
    -0.41
    Bilan
    -0.41
    ulle
    -0.39
    retum
    -0.39
    fill
    -0.38
    duct
    -0.38
    csolódó
    -0.38
     пру
    -0.38
    illi
    -0.37
    POSITIVE LOGITS
    today
    1.19
    TODAY
    1.17
     Today
    1.15
    Today
    1.14
     today
    1.13
     TODAY
    1.07
     Oggi
    0.89
     للاسماء
    0.89
     Tomorrow
    0.87
     oggi
    0.84
    Activations Density 0.030%

    No Known Activations