© 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. 15-GEMMASCOPE-RES-16K
    11. 3571
    Prev
    Next
    INDEX
    Explanations

    references to output statements in code, particularly those that print to the console

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     frattempo
    -0.74
    WebVitals
    -0.69
    +#+#
    -0.64
    eves
    -0.64
     ostavi
    -0.64
    {\"
    -0.59
    interopRequire
    -0.59
     TSS
    -0.58
    呈
    -0.57
     &_
    -0.57
    POSITIVE LOGITS
    Cout
    1.29
     Cout
    1.16
     cout
    1.14
     Coutinho
    1.10
    cout
    1.10
    iostream
    1.03
     Couture
    0.91
     оригіналу
    0.89
     endl
    0.81
    couts
    0.72
    Activations Density 0.034%

    No Known Activations