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. 25-GEMMASCOPE-RES-16K
    6. 4160
    Prev
    Next
    INDEX
    Explanations

    references to specific programming functions or actions within a checkout system

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jois
    -0.49
    inobu
    -0.49
    לוס
    -0.49
    TargetException
    -0.49
    stalt
    -0.49
     متعلقه
    -0.48
     halogen
    -0.48
     AssemblyTitle
    -0.47
     yawn
    -0.47
     studios
    -0.46
    POSITIVE LOGITS
     Order
    1.54
     order
    1.51
     orders
    1.44
    Order
    1.43
    order
    1.41
     Orders
    1.39
     ORDER
    1.31
     getOrder
    1.25
    ORDER
    1.24
    orders
    1.22
    Activations Density 0.299%

    No Known Activations