© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 11149
    Prev
    Next
    INDEX
    Explanations

    terms associated with fading, decay, and decline

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyTitle
    -0.62
     المعيارى
    -0.61
    SPATH
    -0.54
    IntoConstraints
    -0.53
     sockaddr
    -0.52
     '&#
    -0.52
     AssemblyProduct
    -0.52
     houſe
    -0.48
    ValueStyle
    -0.47
     ſp
    -0.46
    POSITIVE LOGITS
     fading
    1.00
     fade
    0.99
     faded
    0.91
     fades
    0.88
     decay
    0.82
    fade
    0.80
     decaying
    0.76
     decline
    0.75
     desvan
    0.74
     decays
    0.73
    Activations Density 0.529%

    No Known Activations