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. 10564
    Prev
    Next
    INDEX
    Explanations

    programming syntax and structure elements in code

    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
    +#+#
    -1.15
    原始内容存档于
    -1.03
    tvguidetime
    -1.03
    ViewImports
    -0.99
    تقاوى
    -0.97
    abestanden
    -0.94
     שוליים
    -0.92
    MemoryWarning
    -0.90
    BeginContext
    -0.90
    دانشنامهٔ
    -0.86
    POSITIVE LOGITS
     alimentaires
    0.48
    hov
    0.42
     commerciali
    0.39
    DM
    0.38
    iv
    0.37
     familiari
    0.37
     ditutup
    0.36
     IV
    0.36
     partenza
    0.36
     artificial
    0.36
    Activations Density 0.310%

    No Known Activations