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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 1396
    Prev
    Next
    INDEX
    Explanations

    information related to individual authors and their contributions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Hungarian names and locations

    np_acts-logits-general · gemini-2.0-flash

    Budapest and Hungarian names

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    PreferredItem
    -0.78
    MessageTagHelper
    -0.69
     Aceh
    -0.67
    IndentedString
    -0.67
    Vanjske
    -0.65
    AsUp
    -0.62
    بالإنجليزية
    -0.60
     iceberg
    -0.60
     felb
    -0.59
    Eksterne
    -0.59
    POSITIVE LOGITS
     Hungarian
    0.88
     Hongrie
    0.84
     Hungary
    0.84
     Budapest
    0.83
    Hungarian
    0.79
     Nagy
    0.77
    Hungary
    0.75
     Magyar
    0.73
     Sze
    0.71
    hung
    0.71
    Activations Density 0.047%

    No Known Activations