© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 11261
    Prev
    Next
    INDEX
    Explanations

    mathematical notation or variables related to structured data

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

    Characters in bracketed coordinate pairs

    np_acts-logits-general · gemini-2.0-flash

    code blocks with curly braces

    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
    
    -0.68
     intptr
    -0.59
    archiviato
    -0.59
    printStackTrace
    -0.58
    期刊论文
    -0.57
     Wikispecies
    -0.54
     useNavigate
    -0.54
     muff
    -0.52
     AssemblyTitle
    -0.52
     cannon
    -0.51
    POSITIVE LOGITS
     {
    1.77
    {
    1.43
     {
    1.13
    \{
    1.12
    ={
    1.10
    /{
    1.08
    ,{
    1.07
     '{
    1.02
    :{
    1.02
     "{
    1.00
    Activations Density 0.794%

    No Known Activations