© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 185
    Prev
    Next
    INDEX
    Explanations

    calculations related to finding the median of a sorted array

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

    code related to calculating the median of an array

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

    mid-point or mid-size

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    rungsseite
    -0.64
     utafitiHapana
    -0.58
     незавершена
    -0.55
    Hochspringen
    -0.54
    fjspx
    -0.52
     Gell
    -0.52
     OMIT
    -0.51
    parsedMessage
    -0.50
    $_['
    -0.50
     superimposed
    -0.48
    POSITIVE LOGITS
     mid
    1.05
    mid
    0.97
    Mid
    0.86
     Mid
    0.84
     midpoint
    0.78
     middle
    0.77
    MID
    0.74
     MID
    0.72
    middle
    0.72
     midden
    0.66
    Activations Density 0.028%

    No Known Activations