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-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 68648
    Prev
    Next
    INDEX
    Explanations

    references to inventions and their historical context in the United States

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

    inventions, innovation, and discoveries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    sidemargin
    -0.59
     FetchType
    -0.44
    Autoritní
    -0.43
     print
    -0.36
    conazole
    -0.35
    دانشنامهٔ
    -0.35
     vacances
    -0.35
     fotografía
    -0.35
     amitié
    -0.35
     empty
    -0.33
    POSITIVE LOGITS
     innovations
    0.77
     inventions
    0.76
     innovation
    0.72
     invention
    0.71
     discoveries
    0.68
    发明
    0.66
     Erfindung
    0.66
    innovation
    0.66
    invention
    0.63
     breakthroughs
    0.62
    Activations Density 0.073%

    No Known Activations