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. 0-GEMMASCOPE-RES-16K
    6. 270
    Prev
    Next
    INDEX
    Explanations

    terms related to technical equipment and devices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ⓧ
    -0.97
    CodeAttribute
    -0.93
     ExecuteAsync
    -0.86
    --]
    -0.86
     Efq
    -0.79
    ArrowToggle
    -0.79
    BeginContext
    -0.78
    lepiej
    -0.75
     ProductService
    -0.74
    ]='\
    -0.74
    POSITIVE LOGITS
     equipment
    1.43
     Equipment
    1.35
    equipment
    1.23
    Device
    1.22
     EQUIPMENT
    1.21
     device
    1.20
    Equipment
    1.19
     devices
    1.14
    设备
    1.13
    device
    1.10
    Activations Density 0.129%

    No Known Activations