© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 238
    Prev
    Next
    INDEX
    Explanations

    phrases indicating time durations or references to years

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

    Duration of time periods

    np_acts-logits-general · gemini-2.0-flash

    long duration or years

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
     recently
    -0.86
     soon
    -0.84
     currently
    -0.82
    recently
    -0.81
     recentemente
    -0.74
    Recently
    -0.72
    currently
    -0.72
    soon
    -0.72
     kürzlich
    -0.69
    originally
    -0.68
    POSITIVE LOGITS
    Continuous
    0.77
     continuously
    0.77
     continuous
    0.76
    PreferredItem
    0.75
     Continuous
    0.74
     uninterrupted
    0.73
     hinweg
    0.73
     steadily
    0.71
    不断
    0.68
    continuous
    0.67
    Activations Density 0.384%

    No Known Activations