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. 20-GEMMASCOPE-RES-16K
    6. 13989
    Prev
    Next
    INDEX
    Explanations

    information related to poverty rates and economic data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/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.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
     EconPapers
    -1.14
    expandindo
    -0.79
     ***!
    -0.78
     الحره
    -0.77
     otomatig
    -0.77
     propOrder
    -0.73
    AnchorTagHelper
    -0.72
     CURIAM
    -0.72
    SharedCtor
    -0.71
     transférez
    -0.70
    POSITIVE LOGITS
     between
    2.30
    Between
    2.06
     Between
    2.01
    between
    2.00
     BETWEEN
    1.79
     mellan
    1.67
     zwischen
    1.61
     tussen
    1.59
    BETWEEN
    1.53
     mellom
    1.40
    Activations Density 1.001%

    No Known Activations