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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 77063
    Prev
    Next
    INDEX
    Explanations

    elements related to factual statements, particularly those indicating being, existence, or essential details about a subject

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
     wireType
    -0.55
     nahilalakip
    -0.52
     LoginForm
    -0.50
    uvwxyz
    -0.50
    Rptr
    -0.49
    Tikang
    -0.48
     ventilation
    -0.47
     EventType
    -0.46
     iNdEx
    -0.46
    しみ
    -0.46
    POSITIVE LOGITS
    RegressionTest
    0.58
     propOrder
    0.49
     productivo
    0.38
     opérés
    0.35
    HtmlAttribute
    0.35
    ValueGenerated
    0.35
    mybatisplus
    0.33
     HttpNotFound
    0.32
    OCCURRED
    0.32
    invokeLater
    0.31
    Activations Density 0.012%

    No Known Activations