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. 5-GEMMASCOPE-RES-16K
    6. 2700
    Prev
    Next
    INDEX
    Explanations

    specific keywords and phrases related to scientific measurements, particularly in the context of electrostatics and biological studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    windowFixed
    -0.70
     EconPapers
    -0.51
     bulk
    -0.47
     Withers
    -0.45
     Fiche
    -0.44
     umani
    -0.42
    şam
    -0.42
    ddot
    -0.41
     paździer
    -0.41
    teht
    -0.40
    POSITIVE LOGITS
    QtWidgets
    0.72
    AnimationsModule
    0.68
     Chwiliwch
    0.67
    Hozzáférés
    0.66
    miyorum
    0.66
    قایناقلار
    0.65
     NavController
    0.65
    modelBuilder
    0.64
     Waray
    0.64
    DotNetBar
    0.64
    Activations Density 3.045%

    No Known Activations