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. 24580
    Prev
    Next
    INDEX
    Explanations

    code-related functions and conditions in programming contexts

    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
     سكانية
    -0.58
     informée
    -0.52
     pungkasnya
    -0.50
    期刊论文
    -0.48
     wciąż
    -0.47
    úgó
    -0.47
    aarrggbb
    -0.44
     newfound
    -0.43
    alised
    -0.43
     gifting
    -0.43
    POSITIVE LOGITS
     }{@
    0.50
    Annexes
    0.46
     للمعارف
    0.43
    IBOutlet
    0.42
    prefixer
    0.40
    soccer
    0.39
    IsContent
    0.39
    processable
    0.38
    Channel
    0.37
    DockStyle
    0.36
    Activations Density 0.018%

    No Known Activations