© 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. 16-GEMMASCOPE-RES-16K
    11. 13513
    Prev
    Next
    INDEX
    Explanations

    citations and references in scholarly documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_16/width_16k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     BoxFit
    -0.51
    ėjimo
    -0.42
     temporales
    -0.41
     anormal
    -0.41
    ckså
    -0.41
     аккура
    -0.41
    Sådan
    -0.41
     tjän
    -0.41
     بيها
    -0.40
    oprot
    -0.40
    POSITIVE LOGITS
     Infórmanos
    0.61
     Italijanski
    0.57
    EndInit
    0.54
    Personendaten
    0.53
    PerformLayout
    0.53
     Roskov
    0.52
     Administrativna
    0.51
     otomatig
    0.50
     kaarangay
    0.50
    IUrlHelper
    0.49
    Activations Density 0.049%

    No Known Activations