© 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. 0-GEMMASCOPE-RES-16K
    11. 12789
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "dynamic" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Engel
    -0.43
    __(/*!
    -0.39
    Pyx
    -0.38
     Silva
    -0.35
     Hay
    -0.35
     Rog
    -0.35
     Construction
    -0.35
    SizedBox
    -0.34
     Cro
    -0.34
     Paul
    -0.34
    POSITIVE LOGITS
     dynamically
    1.96
     dynamic
    1.89
     Dynamic
    1.85
     din
    1.83
     dyna
    1.80
    dynamic
    1.78
    Dynamic
    1.77
     Din
    1.77
    Din
    1.77
     dynamique
    1.70
    Activations Density 0.147%

    No Known Activations