© 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. 9-GEMMASCOPE-RES-16K
    11. 12390
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly dashes, apostrophes, and quotes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     trouw
    -0.48
     مشين
    -0.47
     Füßen
    -0.47
    berdayakan
    -0.47
    IGENCE
    -0.44
     Stücke
    -0.43
     istore
    -0.43
    \{\\
    -0.42
     Justiça
    -0.41
    bloom
    -0.41
    POSITIVE LOGITS
    ("-",
    0.84
     hyphen
    0.80
     "-"
    0.80
     '-':
    0.80
     dashes
    0.80
     dash
    0.79
    ("-");
    0.78
     '-'
    0.77
     "-";
    0.75
     Dash
    0.72
    Activations Density 0.703%

    No Known Activations