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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 1-GEMMASCOPE-RES-16K
    6. 6970
    Prev
    Next
    INDEX
    Explanations

    annotations related to method declarations and properties in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     المعيارى
    -0.62
    +][
    -0.59
    metz
    -0.52
    APOLIS
    -0.52
    dataTables
    -0.52
    identific
    -0.51
    Etimo
    -0.50
    load
    -0.49
    ICZ
    -0.49
    blauch
    -0.49
    POSITIVE LOGITS
    Билгалдахарш
    0.77
    Personendaten
    0.76
     '\\;'
    0.74
     tramonto
    0.73
     autorytatywna
    0.68
     дописавши
    0.67
     OFDb
    0.66
    دانشنامهٔ
    0.66
    Marshal
    0.64
    Демографія
    0.62
    Activations Density 2.058%

    No Known Activations