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. 21-GEMMASCOPE-RES-16K
    6. 2845
    Prev
    Next
    INDEX
    Explanations

    terms and phrases associated with quality and its assessment in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -1.00
     дописавши
    -0.89
    IntoConstraints
    -0.89
    sizeCache
    -0.86
    CloseOperation
    -0.86
    expandindo
    -0.84
    SpringRunner
    -0.79
    GraphicsUnit
    -0.79
    Билгалдахарш
    -0.78
     ویکی‌پدیای
    -0.78
    POSITIVE LOGITS
     assurance
    1.20
     Assurance
    1.01
    Assurance
    0.88
    assurance
    0.86
     quality
    0.82
     control
    0.81
     assured
    0.78
     workmanship
    0.78
     Quality
    0.76
    assured
    0.75
    Activations Density 0.062%

    No Known Activations