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. 62218
    Prev
    Next
    INDEX
    Explanations

    mentions of Ceylon Spinach and related terms

    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
    Theo
    -0.24
     spending
    -0.24
     pocket
    -0.23
     development
    -0.22
     получи
    -0.22
    チャン
    -0.22
     preg
    -0.21
    ừ
    -0.21
     волос
    -0.21
     above
    -0.21
    POSITIVE LOGITS
    يكب
    0.65
    帖最后由
    0.61
    mybatisplus
    0.60
    VersionUID
    0.60
    ItemBackground
    0.59
    AnimationsModule
    0.59
    featureID
    0.58
    PreferredItem
    0.58
    StoreMessageInfo
    0.58
     تضيفلها
    0.57
    Activations Density 0.053%

    No Known Activations