Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 13701
    Prev
    Next
    INDEX
    Explanations

    references to online retail platforms and their features

    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
    ########.
    -0.54
     Viitattu
    -0.49
    ymce
    -0.48
     تانيه
    -0.48
     ICF
    -0.48
    badah
    -0.47
     ENGINEERS
    -0.47
    Vidite
    -0.46
     Einladung
    -0.45
     Scholarships
    -0.45
    POSITIVE LOGITS
     shopping
    2.21
     shop
    2.05
     shops
    1.91
     retail
    1.89
     shoppers
    1.89
     Shopping
    1.87
     Shop
    1.84
     retailers
    1.77
    Shop
    1.76
     store
    1.74
    Activations Density 0.598%

    No Known Activations