© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 7995
    Prev
    Next
    INDEX
    Explanations

    references to flash memory technology

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

    Mention of "flash" memory

    np_acts-logits-general · gemini-2.0-flash

    flash memory and OS

    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
     nakalista
    -0.83
    TagMode
    -0.82
    expandindo
    -0.81
    principalTable
    -0.81
     propOrder
    -0.79
    AddTagHelper
    -0.78
    ISupport
    -0.75
    IndentedString
    -0.75
     preocupes
    -0.73
    LEGGI
    -0.73
    POSITIVE LOGITS
     flash
    0.94
    flash
    0.80
     Flash
    0.80
     FLASH
    0.72
    Flash
    0.72
     flashes
    0.68
     flas
    0.66
     Flas
    0.64
    FLASH
    0.62
     flashed
    0.61
    Activations Density 0.109%

    No Known Activations