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. 1623
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to various industries and sectors

    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
    полнитель
    -0.68
    Scor
    -0.68
    zep
    -0.67
    pran
    -0.66
    scor
    -0.66
     normaal
    -0.66
     olympique
    -0.65
    sniper
    -0.64
     Amad
    -0.64
     umane
    -0.64
    POSITIVE LOGITS
     industry
    2.14
     Industry
    2.06
    industry
    1.94
    Industry
    1.92
     industries
    1.83
     INDUSTRY
    1.73
     industrie
    1.48
     Industries
    1.43
    industrie
    1.42
    INDUSTRY
    1.41
    Activations Density 0.023%

    No Known Activations