© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 4873
    Prev
    Next
    INDEX
    Explanations

    calls to the 'println' method in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     noDo
    -0.51
     disambiguazione
    -0.49
     useAuth
    -0.49
     poire
    -0.49
    Referencies
    -0.48
    Donor
    -0.47
    点此举报
    -0.47
    icoot
    -0.47
     tiguan
    -0.46
     ſta
    -0.46
    POSITIVE LOGITS
    println
    2.67
     println
    1.66
    WriteLine
    1.63
    Println
    1.32
    AppendLine
    1.26
    writeln
    0.75
     AssemblyTitle
    0.69
    writerow
    0.67
    cout
    0.64
     endl
    0.60
    Activations Density 0.036%

    No Known Activations