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. 1780
    Prev
    Next
    INDEX
    Explanations

    references to academic institutions and geographical locations

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

    Italy or Italian language

    np_acts-logits-general · gemini-2.0-flash

    Italian places, people, and food

    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
     Monfieur
    -1.08
     Majefty
    -0.95
     Theſe
    -0.94
     متعلقه
    -0.93
     myſelf
    -0.91
     Efq
    -0.89
     Jefus
    -0.87
     titolata
    -0.86
     Houſe
    -0.85
     CHAPITRE
    -0.84
    POSITIVE LOGITS
     Italian
    1.17
     Italy
    1.11
    Italian
    1.04
    Italy
    1.02
     Italians
    0.96
     Итали
    0.89
     Italia
    0.89
     italian
    0.89
     włos
    0.86
     italien
    0.84
    Activations Density 0.226%

    No Known Activations