© 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. 20-GEMMASCOPE-RES-16K
    11. 1041
    Prev
    Next
    INDEX
    Explanations

    unique identifiers or headers in the text

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

    Inside parentheses or brackets

    np_acts-logits-general · gemini-2.0-flash

    citations and academic formatting

    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
    Personensuche
    -0.87
    basicConfig
    -0.86
    */),
    -0.85
    Билгалдахарш
    -0.85
     tartalomajánló
    -0.84
    principalColumn
    -0.81
    
    -0.81
    SharedDtor
    -0.81
     ()
    -0.81
     ProtoMessage
    -0.81
    POSITIVE LOGITS
    <
    0.85
    [toxicity=0]
    0.85
    <strong>
    0.66
    Q
    0.65
    [
    0.65
     <
    0.60
      
    0.56
    <b>
    0.55
     The
    0.55
     It
    0.53
    Activations Density 0.673%

    No Known Activations