© 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. 4396
    Prev
    Next
    INDEX
    Explanations

    references to specific years and significant events or milestones

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

    a specific year

    np_acts-logits-general · gemini-2.0-flash

    yearly 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
    aarrggbb
    -0.51
     monthly
    -0.47
    后期
    -0.47
     @{
    -0.47
     fortnight
    -0.46
    ARROLLO
    -0.45
     daily
    -0.45
     comb
    -0.44
    onday
    -0.44
    EMBLE
    -0.44
    POSITIVE LOGITS
    今年は
    1.66
     year
    1.65
     tahun
    1.53
     Year
    1.52
    Year
    1.50
    year
    1.45
    今年も
    1.45
    今年
    1.41
     année
    1.38
     YEAR
    1.36
    Activations Density 0.491%

    No Known Activations