© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 9207
    Prev
    Next
    INDEX
    Explanations

    keywords and comments related to programming logic and structure

    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
    ?&
    -0.51
    hisattva
    -0.51
     ferdig
    -0.50
    accesorios
    -0.49
    ?】
    -0.48
    )}
    
    -0.48
    charpe
    -0.48
     finnas
    -0.47
    ))-
    -0.47
    paksa
    -0.47
    POSITIVE LOGITS
    NSLog
    1.01
    println
    0.98
    print
    0.97
    console
    0.91
     println
    0.90
    printf
    0.88
    Console
    0.87
    qDebug
    0.80
    puts
    0.79
    logger
    0.76
    Activations Density 0.270%

    No Known Activations