© 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. 4468
    Prev
    Next
    INDEX
    Explanations

    statistics and numerical data related to demographics and measurements

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

    Words/tokens near "average"

    np_acts-logits-general · gemini-2.0-flash

    average

    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
    RowCount
    -0.48
     సౌకర్య
    -0.46
    beiros
    -0.45
    gence
    -0.43
    luit
    -0.43
    Pranala
    -0.43
    MUM
    -0.43
    hi
    -0.42
    Transkript
    -0.41
    ณี
    -0.41
    POSITIVE LOGITS
     average
    2.46
     Average
    2.23
    Average
    2.21
    average
    2.16
     averages
    2.02
     averaged
    1.94
     AVERAGE
    1.90
    平均
    1.89
     avg
    1.81
     averaging
    1.81
    Activations Density 0.575%

    No Known Activations