© 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-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 5117
    Prev
    Next
    INDEX
    Explanations

    phrases related to ease of use and successful outcomes in processes

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

    "smooth" or "smoothly" actions

    np_acts-logits-general · gemini-2.0-flash

    actions happening smoothly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 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
    hnia
    -0.58
     hypocrite
    -0.58
    httphttps
    -0.55
    enumi
    -0.54
     Pharisees
    -0.51
     humble
    -0.51
     onCreateView
    -0.50
     geri
    -0.50
     modesty
    -0.49
    auru
    -0.48
    POSITIVE LOGITS
     smooth
    2.23
     Smooth
    2.07
     smoothly
    2.00
     smoother
    1.98
    Smooth
    1.92
    smooth
    1.89
     smoothness
    1.85
     seamless
    1.58
     SMO
    1.54
     smoothed
    1.45
    Activations Density 0.185%

    No Known Activations