© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 6915
    Prev
    Next
    INDEX
    Explanations

    technical terms related to gauge theory and its application in physics

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

    after "Spice", "gauge", or "nurse"

    np_acts-logits-general · gemini-2.0-flash

    gauge theories and dependence

    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
    ness
    -1.61
    nya
    -1.27
    n
    -0.85
    ers
    -0.81
    d
    -0.80
    了
    -0.79
    ding
    -0.79
    isation
    -0.78
    name
    -0.78
    🏼
    -0.77
    POSITIVE LOGITS
    e
    1.00
    eeeeeeee
    0.90
    eeee
    0.85
    eeeee
    0.81
     createSlice
    0.80
    eee
    0.78
    ourite
    0.75
     useNavigate
    0.74
     INA
    0.73
    eeeeee
    0.73
    Activations Density 1.976%

    No Known Activations