© 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. 16-GEMMASCOPE-RES-16K
    11. 6788
    Prev
    Next
    INDEX
    Explanations

    mentions of time durations and intervals in a scientific context

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

    Time measurements (minutes, days, weeks, years)

    np_acts-logits-general · gemini-2.0-flash

    time durations and intervals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Duration
    -0.56
    Duration
    -0.52
    しばらく
    -0.52
     lasts
    -0.51
     lasted
    -0.51
     briefly
    -0.49
    一段时间
    -0.47
     brief
    -0.46
     Briefly
    -0.45
     momentary
    -0.44
    POSITIVE LOGITS
    ArgsConstructor
    0.82
    Datuak
    0.80
     CreateTagHelper
    0.79
    AndEndTag
    0.75
    StructEnd
    0.73
    RegressionTest
    0.72
    parsedMessage
    0.71
     незавершена
    0.71
    SPATH
    0.70
     BorderSide
    0.67
    Activations Density 0.472%

    No Known Activations