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. 5-GEMMASCOPE-RES-16K
    6. 11981
    Prev
    Next
    INDEX
    Explanations

    numerical values and percentages related to measurements or quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     byg
    -0.60
    AddHtmlAttribute
    -0.54
    enumi
    -0.52
     boy
    -0.51
     investors
    -0.48
     raising
    -0.47
    6
    -0.46
    弥
    -0.45
     nor
    -0.45
     TRACE
    -0.45
    POSITIVE LOGITS
    Geplaatst
    0.87
     jScrollPane
    0.83
    VersionUID
    0.75
     }}"></
    0.71
    存于互联网档案馆
    0.68
     transférez
    0.67
    openzeppelin
    0.67
    
    0.67
    "]];
    0.66
     سكانية
    0.66
    Activations Density 0.343%

    No Known Activations