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. 15-GEMMASCOPE-RES-16K
    6. 2456
    Prev
    Next
    INDEX
    Explanations

    the keyword "request" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dalamnya
    -0.74
    AfterClass
    -0.74
    __":
    
    -0.70
    ειτουργ
    -0.62
     dõi
    -0.60
    artament
    -0.59
     TDA
    -0.59
    hauled
    -0.59
     Melton
    -0.59
    发表于
    -0.58
    POSITIVE LOGITS
     Request
    1.37
     request
    1.32
     requests
    1.32
     getRequest
    1.29
     REQUEST
    1.28
    getRequest
    1.25
    REQUEST
    1.23
     Requests
    1.23
    Request
    1.22
    request
    1.21
    Activations Density 0.094%

    No Known Activations