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. 12-GEMMASCOPE-RES-16K
    6. 11884
    Prev
    Next
    INDEX
    Explanations

    cooking instructions and ingredients

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SourceChecksum
    -1.01
     myſelf
    -0.95
    ſelf
    -0.95
    ⓧ
    -0.94
     himſelf
    -0.91
     becauſe
    -0.90
     itſelf
    -0.88
     whoſe
    -0.87
     purpoſe
    -0.87
    IonicModule
    -0.87
    POSITIVE LOGITS
     toppings
    0.53
     aggiungere
    0.52
     topping
    0.47
    mis
    0.47
     aggiunge
    0.44
     aggiunto
    0.43
     hu
    0.43
     ajouter
    0.42
     menambahkan
    0.42
     sprinkle
    0.42
    Activations Density 0.166%

    No Known Activations