© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 752
    Prev
    Next
    INDEX
    Explanations

    phrases related to smoothness and seamlessness in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "smooth"

    np_acts-logits-general · gemini-2.0-flash

    smooth movement, operation, or transition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     repuesto
    -0.49
     hodnot
    -0.48
     JpaRepository
    -0.48
     []:
    -0.48
     féd
    -0.47
     wartości
    -0.47
     Normdatei
    -0.46
     mijne
    -0.46
     camiset
    -0.45
     fotográfica
    -0.45
    POSITIVE LOGITS
    smooth
    1.29
     smooth
    1.27
     Smooth
    1.24
    Smooth
    1.20
     smoothly
    1.16
     smoothness
    1.14
     smoother
    1.03
     smoothed
    1.02
     SMO
    0.90
     smoothing
    0.88
    Activations Density 0.120%

    No Known Activations