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. 73626
    Prev
    Next
    INDEX
    Explanations

    terms related to division or separation

    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
     للمعارف
    -0.61
    userManager
    -0.56
    ayer
    -0.56
     NavController
    -0.55
    elerik
    -0.55
    BeginContext
    -0.55
     FetchType
    -0.53
    erci
    -0.50
     userName
    -0.49
    fortawesome
    -0.49
    POSITIVE LOGITS
    split
    1.15
     split
    1.10
    Split
    1.02
     Split
    1.00
    splits
    0.89
    SPLIT
    0.88
     splits
    0.86
     splitting
    0.83
    splitting
    0.78
    plit
    0.76
    Activations Density 0.009%

    No Known Activations