© 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. 15-GEMMASCOPE-RES-16K
    11. 1799
    Prev
    Next
    INDEX
    Explanations

    parameters and configurations related to window and video settings in a coding context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 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
     conocemos
    -0.41
     accuses
    -0.39
     accuse
    -0.39
     niega
    -0.39
     RemoteException
    -0.38
     kayna
    -0.38
     Nachweis
    -0.38
     advertencia
    -0.37
     inocente
    -0.36
     verschill
    -0.36
    POSITIVE LOGITS
    تقاوى
    0.53
    الحياه
    0.53
     CGSize
    0.52
    figsize
    0.52
    setVerticalGroup
    0.52
     Мексичка
    0.51
    ClientRect
    0.50
    viewBox
    0.50
    DockStyle
    0.50
     rectangular
    0.49
    Activations Density 0.309%

    No Known Activations