© 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. 3907
    Prev
    Next
    INDEX
    Explanations

    file handling and input/output operations in coding

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

    Code file writing and closing

    np_acts-logits-general · gemini-2.0-flash

    write, flush, close

    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
    ReusableCell
    -0.77
    BufferException
    -0.70
     kasarigan
    -0.69
    
    -0.68
    abetes
    -0.68
     externi
    -0.68
    adaptiveStyles
    -0.68
     esternos
    -0.64
     للمعارف
    -0.63
     pinulongan
    -0.62
    POSITIVE LOGITS
    close
    0.49
    LLocation
    0.49
     close
    0.48
    iello
    0.42
     SEEK
    0.41
     vote
    0.41
     clogs
    0.40
    SEEK
    0.40
     clog
    0.40
     hemel
    0.39
    Activations Density 0.088%

    No Known Activations