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. 122654
    Prev
    Next
    INDEX
    Explanations

    technical terms and phrases related to conditions, definitions, and legal language

    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
     تضيفلها
    -0.60
    :✨
    -0.60
     مرئيه
    -0.56
     nahilalakip
    -0.52
    UVWXYZ
    -0.50
    ronpa
    -0.48
    __":
    
    -0.48
     لينك
    -0.48
     informée
    -0.46
     ſur
    -0.46
    POSITIVE LOGITS
    ьажоргаш
    0.48
     astore
    0.44
    Reprodução
    0.41
     HCM
    0.40
     мәкал
    0.40
     potr
    0.40
    bitField
    0.40
    ivent
    0.40
    riol
    0.39
     Guter
    0.38
    Activations Density 0.309%

    No Known Activations