© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 9173
    Prev
    Next
    INDEX
    Explanations

    mathematical terms related to optimization and performance analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rät
    -0.37
     أق
    -0.36
    estimm
    -0.35
    URLConnection
    -0.34
     Screen
    -0.33
     сда
    -0.32
     QI
    -0.32
    KommentareTeilen
    -0.32
    Bea
    -0.32
     Bik
    -0.32
    POSITIVE LOGITS
     rospy
    0.84
    chartInstance
    0.62
     contextLoads
    0.62
    apunov
    0.59
    ulink
    0.58
     robotics
    0.54
    AnimationsModule
    0.54
     control
    0.50
    rospy
    0.50
    úgó
    0.49
    Activations Density 0.815%

    No Known Activations