© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 6295
    Prev
    Next
    INDEX
    Explanations

    words related to the creation and generation of items or functions

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

    Code related to "create" or "creation"

    np_acts-logits-general · gemini-2.0-flash

    create

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tqdm
    -0.59
    webElementXpaths
    -0.56
    
    -0.55
    Strap
    -0.54
     ChromeDriver
    -0.54
     Corde
    -0.54
    Shri
    -0.53
    prechpartner
    -0.53
    wob
    -0.53
     marins
    -0.52
    POSITIVE LOGITS
    /−
    0.84
     Creates
    0.83
     creators
    0.81
    Creates
    0.81
     Creation
    0.79
     creations
    0.78
     creation
    0.77
     Creators
    0.74
     creates
    0.73
     Layton
    0.72
    Activations Density 0.093%

    No Known Activations