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. 4709
    Prev
    Next
    INDEX
    Explanations

    sections of markup or content that are empty or have minimal content

    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
    parametrize
    -0.66
     فريبيس
    -0.62
    moveToNext
    -0.59
    Personensuche
    -0.57
     समीक्षाओं
    -0.54
     otomatig
    -0.52
    styleType
    -0.51
     moverse
    -0.51
     nicio
    -0.51
    RunAsync
    -0.50
    POSITIVE LOGITS
     pageContext
    0.62
    Бахар
    0.56
    >(&
    0.56
    tagHelperRunner
    0.55
    Einzelnachweise
    0.55
     initComponents
    0.55
     jsPsych
    0.55
      
    0.54
    bleau
    0.53
    camp
    0.53
    Activations Density 0.089%

    No Known Activations