© 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. 8-GEMMASCOPE-RES-16K
    6. 10895
    Prev
    Next
    INDEX
    Explanations

    terms related to artistic expression and creativity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/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.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Borel
    -0.48
    一旦
    -0.47
    intracht
    -0.47
    表示
    -0.47
    DeleteBehavior
    -0.45
     psicológico
    -0.43
    Diwedd
    -0.42
    liche
    -0.42
    FontAwesomeIcon
    -0.41
     Duitse
    -0.41
    POSITIVE LOGITS
     createSprite
    0.77
    :✨
    0.71
     كومونز
    0.70
    ///</
    0.69
    verwijspagina
    0.68
    Empereur
    0.67
    
    0.67
    VideoCapture
    0.65
    SharedDtor
    0.64
     المعيارى
    0.64
    Activations Density 1.985%

    No Known Activations