© 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-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 6929
    Prev
    Next
    INDEX
    Explanations

    references to announcements, reports, and formal communications related to events or decisions

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

    time, especially years and months

    np_acts-logits-general · gemini-2.0-flash

    previous time references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tomorrow
    -1.32
     tonight
    -1.23
    tomorrow
    -1.07
     today
    -1.03
     todays
    -0.99
     demain
    -0.97
    Tomorrow
    -0.94
    Tonight
    -0.94
    today
    -0.92
    今日の
    -0.88
    POSITIVE LOGITS
     earlier
    1.10
     damals
    1.07
     previously
    1.01
    當時
    0.99
    当时
    0.96
     Earlier
    0.93
    Previously
    0.91
    earlier
    0.90
     Previously
    0.89
    Earlier
    0.86
    Activations Density 0.328%

    No Known Activations