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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 14677
    Prev
    Next
    INDEX
    Explanations

    references to time periods and sequences

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

    Time periods, often fractions of a year

    np_acts-logits-general · gemini-2.0-flash

    first parts of time

    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
    ViewImports
    -0.54
    WaitGroup
    -0.51
     ciasc
    -0.48
     HttpNotFound
    -0.48
    ArrowToggle
    -0.47
    esModule
    -0.47
     ujednoznacz
    -0.46
    brite
    -0.45
     altrett
    -0.45
    MemoryWarning
    -0.45
    POSITIVE LOGITS
     part
    0.99
     stages
    0.82
     days
    0.76
     phase
    0.76
     portion
    0.76
     half
    0.76
     leg
    0.73
    stages
    0.72
     phases
    0.69
     hours
    0.69
    Activations Density 0.195%

    No Known Activations