© 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 - 65k
    9. 13-GEMMASCOPE-RES-65K
    11. 22175
    Prev
    Next
    INDEX
    Explanations

    punctuation marks that typically indicate the end of a statement or section

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     colorés
    -0.74
    ͅ
    -0.66
     marins
    -0.65
    //
    -0.63
     foncé
    -0.61
     supérieurs
    -0.59
     levure
    -0.58
     hindurch
    -0.58
     serca
    -0.58
     sonno
    -0.57
    POSITIVE LOGITS
    ...</
    1.71
    :</
    1.64
    -</
    1.27
    .</
    1.27
     :</
    1.22
    ?</
    1.20
    ----</
    1.18
    ).</
    1.09
    ."</
    1.09
    !</
    1.07
    Activations Density 0.004%

    No Known Activations