© 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. 21-GEMMASCOPE-RES-16K
    6. 12999
    Prev
    Next
    INDEX
    Explanations

    elements related to image processing and transformations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    )]{
    -0.48
    ]='\
    -0.45
     Mou
    -0.45
    (""))
    -0.44
     Post
    -0.44
    )][
    -0.43
     محفوظة
    -0.43
    '])->
    -0.42
    AddHtmlAttribute
    -0.42
    )):
    
    -0.41
    POSITIVE LOGITS
     zeros
    0.91
    ones
    0.75
    zeros
    0.74
     ones
    0.73
    saraba
    0.68
    IBarButtonItem
    0.67
     Chwiliwch
    0.64
     kasarigan
    0.64
    
    0.64
    FontOfSize
    0.62
    Activations Density 0.400%

    No Known Activations