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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 13183
    Prev
    Next
    INDEX
    Explanations

    elements of time and sequence in events

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

    expressions of time including days, weeks, nights, and temporal durations.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
     EconPapers
    -0.72
    transQ
    -0.66
     propOrder
    -0.65
     surla
    -0.65
    AndEndTag
    -0.65
    ftagPool
    -0.63
    IsContent
    -0.60
    ⓧ
    -0.57
    recated
    -0.57
    sizeCache
    -0.57
    POSITIVE LOGITS
     afterwards
    0.36
    URIComponent
    0.33
     Afterwards
    0.32
    Afterwards
    0.32
    翌日
    0.31
     Hanging
    0.31
     chronic
    0.31
     Afterward
    0.30
    gangenen
    0.30
     mailbox
    0.30
    Activations Density 0.391%

    No Known Activations