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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 9921
    Prev
    Next
    INDEX
    Explanations

    references to business operations and recommendations for service providers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /**
    -0.71
    出版年
    -0.70
     EconPapers
    -0.67
    脚注の使い方
    -0.61
    AutoScaleMode
    -0.59
    帖最后由
    -0.58
    WebElementEntity
    -0.58
    IUrlHelper
    -0.57
    ashier
    -0.56
     ujednoznacz
    -0.56
    POSITIVE LOGITS
     hire
    1.84
     hiring
    1.82
     hired
    1.77
     Hire
    1.57
    Hire
    1.57
     hires
    1.56
     Hiring
    1.53
     contratar
    1.47
    Hiring
    1.47
     entrust
    1.38
    Activations Density 0.328%

    No Known Activations