© 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. 5475
    Prev
    Next
    INDEX
    Explanations

    references to dates and sequences of events

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

    the passage of time

    np_acts-logits-general · gemini-2.0-flash

    days following or preceding

    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
     ExecuteAsync
    -0.81
    exitRule
    -0.74
     Vergangenheit
    -0.71
    parsedMessage
    -0.70
     autrefois
    -0.70
    principalTable
    -0.67
    躇
    -0.67
    findpost
    -0.67
     gawas
    -0.64
    //
    -0.64
    POSITIVE LOGITS
    翌
    0.91
     day
    0.85
     following
    0.84
     lendemain
    0.80
     night
    0.74
     next
    0.72
     week
    0.70
    翌日
    0.69
    following
    0.68
    Immediately
    0.66
    Activations Density 0.128%

    No Known Activations