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. 16361
    Prev
    Next
    INDEX
    Explanations

    the beginning of a document or section, often marked by opening tokens

    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
     CreateTagHelper
    -0.84
    principalTable
    -0.75
    HasForeignKey
    -0.73
     تضيفلها
    -0.71
    onOptions
    -0.69
    >>>>>>>>
    -0.67
    脚注の使い方
    -0.67
     BoxDecoration
    -0.66
     ……………………
    -0.65
    SequentialGroup
    -0.65
    POSITIVE LOGITS
     jouet
    0.56
     traseira
    0.54
    <bos>
    0.53
     digitais
    0.53
     comerciais
    0.53
     tatouage
    0.52
     financeira
    0.51
     jouets
    0.49
     fédé
    0.49
     démocr
    0.48
    Activations Density 0.432%

    No Known Activations