© 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-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 14291
    Prev
    Next
    INDEX
    Explanations

    elements of mathematical notation and formatting

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

    mathematical equations and LaTeX code structures with complex formatting.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.77
    astéro
    -0.76
     queſta
    -0.74
    KommentareTeilen
    -0.73
     MainAxisSize
    -0.71
     dieſe
    -0.69
     deſt
    -0.69
     StatelessWidget
    -0.69
     raiſ
    -0.68
     ſte
    -0.68
    POSITIVE LOGITS
    </strong>
    0.87
    </em>
    0.85
    </b>
    0.72
    </i>
    0.66
    </u>
    0.62
    </code>
    0.62
    </h3>
    0.50
    hline
    0.50
    </h4>
    0.48
    hdashline
    0.48
    Activations Density 0.185%

    No Known Activations