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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 8432
    Prev
    Next
    INDEX
    Explanations

    terms related to physical structures and components across various contexts

    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
    IUrlHelper
    -0.77
     disambiguazione
    -0.75
     linkovi
    -0.73
    URLException
    -0.73
    :✨
    -0.70
    DockStyle
    -0.70
     ujednoznacz
    -0.70
     propOrder
    -0.69
    AddTagHelper
    -0.68
     Biôgrafia
    -0.68
    POSITIVE LOGITS
     règne
    0.33
     trône
    0.30
     prestaciones
    0.27
     adentro
    0.26
     drapeau
    0.26
     bénéficiaire
    0.26
    ModelBuilder
    0.25
     asegurado
    0.23
     asegu
    0.23
     cubierto
    0.22
    Activations Density 0.274%

    No Known Activations