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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 23-GEMMASCOPE-RES-16K
    6. 12465
    Prev
    Next
    INDEX
    Explanations

    phrases related to cleaning and maintenance of surfaces and materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RegressionTest
    -0.79
     ویکی‌پدیا
    -0.78
     disambiguazione
    -0.77
     CreateTagHelper
    -0.74
     AssemblyProduct
    -0.72
     nahilalakip
    -0.72
    fromnode
    -0.70
     ***!
    -0.69
     informée
    -0.68
    Personensuche
    -0.68
    POSITIVE LOGITS
     dust
    1.08
     dirt
    1.05
     debris
    1.02
     grime
    0.83
    dirt
    0.80
    dust
    0.80
     impurities
    0.80
     residue
    0.78
     Debris
    0.76
     detr
    0.75
    Activations Density 0.361%

    No Known Activations