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. 1236
    Prev
    Next
    INDEX
    Explanations

    references to third-party entities or vendors

    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
     Wittenberg
    -0.61
     ausz
    -0.56
    endő
    -0.55
     getLayout
    -0.55
     productivo
    -0.51
     karar
    -0.50
     suivie
    -0.49
     enfermo
    -0.48
     cumplido
    -0.48
    workbook
    -0.48
    POSITIVE LOGITS
    第三方
    1.04
     terceiros
    1.00
     terceros
    0.96
     vendor
    0.85
     parties
    0.84
     vendors
    0.84
     third
    0.83
     external
    0.83
     THIRD
    0.81
    Parties
    0.80
    Activations Density 0.120%

    No Known Activations