Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 105281
    Prev
    Next
    INDEX
    Explanations

    terms and relationships in mathematical or theoretical frameworks related to models and equations

    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
     وتسجيلات
    -0.54
    BibitemShut
    -0.53
    Искәрмәләр
    -0.53
    存于互联网档案馆
    -0.49
     '\\;'
    -0.49
    HasForeignKey
    -0.48
     kasarigan
    -0.47
    tanleria
    -0.47
    istoitu
    -0.46
    цездатний
    -0.46
    POSITIVE LOGITS
     mentioned
    0.49
    mentioned
    0.42
    ințe
    0.40
     again
    0.40
    arakat
    0.37
     CreateTagHelper
    0.36
     mencionado
    0.36
    MessageOf
    0.35
    🖨
    0.33
     onOptions
    0.33
    Activations Density 0.326%

    No Known Activations