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. 12457
    Prev
    Next
    INDEX
    Explanations

    sequences of numbers and codes related to programming or data processing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    3
    -0.69
     Wednesday
    -0.64
    Wednesday
    -0.56
     الأربع
    -0.54
    ३
    -0.52
     WEDNESDAY
    -0.50
    3
    -0.50
    rolid
    -0.47
    
    -0.47
    4
    -0.47
    POSITIVE LOGITS
     Saturday
    1.24
    Saturday
    1.18
     Sunday
    1.14
     saturday
    1.10
    Sunday
    1.10
     SUNDAY
    1.06
     SATURDAY
    1.05
     sunday
    1.02
    SATURDAY
    1.02
     sábado
    0.98
    Activations Density 0.325%

    No Known Activations