© 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. 3414
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions or equations related to probability and statistics

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

    Mathematical or scientific equations

    np_acts-logits-general · gemini-2.0-flash

    latex math delimiters

    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
    CharStream
    -0.58
    argout
    -0.50
    قایناق‌لار
    -0.48
    landt
    -0.47
    RAINT
    -0.46
    ingual
    -0.45
    lihood
    -0.45
    djangoproject
    -0.45
    var
    -0.44
    kmäler
    -0.44
    POSITIVE LOGITS
     {
    1.30
     {
    
    1.02
    ,{
    0.99
    {
    0.95
     {{
    0.94
    ={{
    0.92
    {
    
    0.87
    ',{
    0.83
    ",{
    0.83
     {.
    0.83
    Activations Density 0.708%

    No Known Activations