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. 8655
    Prev
    Next
    INDEX
    Explanations

    verbs that indicate completed actions or significant changes

    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
     âgées
    -0.63
     Eventually
    -0.60
     soon
    -0.59
     CreateTagHelper
    -0.59
    Eventually
    -0.58
     eventually
    -0.57
    :✨
    -0.56
    eventually
    -0.55
     segera
    -0.54
     Annales
    -0.54
    POSITIVE LOGITS
     since
    1.09
     recientemente
    1.03
    since
    0.97
     SINCE
    0.96
     recentemente
    0.95
     sejak
    0.87
    Since
    0.86
     recently
    0.84
     للتو
    0.83
     lately
    0.83
    Activations Density 0.192%

    No Known Activations