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-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 114900
    Prev
    Next
    INDEX
    Explanations

    references to duality or comparisons between two sides or aspects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     aller
    -0.36
     réfugiés
    -0.35
    ниципа
    -0.33
     arché
    -0.33
     certains
    -0.33
     '<?
    -0.33
     âmes
    -0.33
     lecturer
    -0.33
     professor
    -0.32
     getCategory
    -0.32
    POSITIVE LOGITS
    ArrowToggle
    0.64
     MainAxisSize
    0.64
     Beide
    0.62
    DockStyle
    0.59
     Sides
    0.58
    tagHelperRunner
    0.58
    InputBorder
    0.57
     sides
    0.55
    AnchorStyles
    0.55
     beider
    0.55
    Activations Density 0.029%

    No Known Activations