Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 13703
    Prev
    Next
    INDEX
    Explanations

    references to the color pink and its various associations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
     Normdatei
    -0.96
     ComVisible
    -0.85
    NameInMap
    -0.73
    esModule
    -0.72
    sizeCache
    -0.70
     ainfi
    -0.68
    AsUp
    -0.67
    dafx
    -0.66
     protoimpl
    -0.65
    存于互联网档案馆
    -0.63
    POSITIVE LOGITS
     haired
    0.60
    haired
    0.56
     colored
    0.54
    $_['
    0.51
     coloured
    0.50
    mar
    0.50
     light
    0.49
     color
    0.49
     Label
    0.49
     ang
    0.48
    Activations Density 0.130%

    No Known Activations