© 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. 4540
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "May" and its variations or contexts related to dates and events in May

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

    the word "May"

    np_acts-logits-general · gemini-2.0-flash

    month or month-related phrases

    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
    rungsseite
    -0.79
    ViewImports
    -0.74
    RegistryLite
    -0.74
    TypedDataSet
    -0.71
    ModelAdmin
    -0.69
     ligiloj
    -0.66
    orcid
    -0.66
    </tbody>
    -0.65
     المعيارى
    -0.64
     numberWith
    -0.64
    POSITIVE LOGITS
     mắn
    1.02
    May
    0.94
    MAY
    0.92
     May
    0.87
     MAY
    0.85
     Mays
    0.76
     Mayhem
    0.70
    onnaise
    0.69
    may
    0.68
     Maynard
    0.65
    Activations Density 0.051%

    No Known Activations