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. 8086
    Prev
    Next
    INDEX
    Explanations

    special characters or symbols used in various contexts

    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
     snippetHide
    -0.77
     queſta
    -0.74
     Мексичка
    -0.74
     незавершена
    -0.67
    berdayakan
    -0.66
     sánchez
    -0.66
    تقاوى
    -0.65
    sizeCache
    -0.65
     Normdatei
    -0.63
    Personendaten
    -0.63
    POSITIVE LOGITS
    ↵
    0.47
    <em>
    0.47
    <strong>
    0.46
    As
    0.45
     also
    0.45
    <b>
    0.44
        
    0.43
    lf
    0.43
      
    0.43
    .
    0.43
    Activations Density 0.142%

    No Known Activations