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-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 5090
    Prev
    Next
    INDEX
    Explanations

    words and phrases that convey energy, liveliness, and vibrant experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     nahilalakip
    -0.54
    ="../../
    -0.47
    Erreferentziak
    -0.46
    FileChooser
    -0.44
     Hague
    -0.43
    ttino
    -0.42
     Picchu
    -0.42
     postIndex
    -0.42
     NSCoder
    -0.42
    DockStyle
    -0.42
    POSITIVE LOGITS
     dynamism
    0.80
     vitality
    0.79
     vibrant
    0.76
     Vitality
    0.75
     lively
    0.74
    dynamic
    0.73
     dinam
    0.72
     dynamis
    0.71
     vigor
    0.71
     dynamic
    0.71
    Activations Density 0.278%

    No Known Activations