Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 7985
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "May" or related variations indicative of the month

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

    "May"

    np_acts-logits-general · gemini-2.0-flash

    May

    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
    ModelAdmin
    -0.81
    RegistryLite
    -0.66
     newState
    -0.66
    rungsseite
    -0.65
    RTEX
    -0.64
    ViewImports
    -0.61
     ligiloj
    -0.61
     Reisedaten
    -0.59
     <<<<<<<<<<<<<<
    -0.57
     pinulongan
    -0.56
    POSITIVE LOGITS
     mắn
    0.97
    May
    0.78
    MAY
    0.75
    onnaise
    0.73
     MAY
    0.72
    fair
    0.71
     May
    0.71
    hew
    0.65
    flower
    0.65
     Mayhem
    0.64
    Activations Density 0.060%

    No Known Activations