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. 24-GEMMASCOPE-RES-16K
    6. 4522
    Prev
    Next
    INDEX
    Explanations

    temporal expressions and phrases related to events or actions occurring in the future or specific timeframes

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

    Months after a preposition

    np_acts-logits-general · gemini-2.0-flash

    months and time periods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Бахар
    -0.89
    GraphicsUnit
    -0.83
     AssemblyCulture
    -0.83
     tomorrow
    -0.76
     שוליים
    -0.75
    Tomorrow
    -0.72
     amanhã
    -0.70
     demain
    -0.69
    tomorrow
    -0.68
     ویکی‌پدی
    -0.67
    POSITIVE LOGITS
     late
    2.15
     early
    2.05
    early
    1.72
     mid
    1.72
    late
    1.70
    Late
    1.56
     Late
    1.49
     LATE
    1.44
    Early
    1.43
     Early
    1.42
    Activations Density 0.209%

    No Known Activations