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. 117383
    Prev
    Next
    INDEX
    Explanations

    variable assignments and return statements in programming code

    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
    ✷
    -0.41
     régimen
    -0.40
    pektive
    -0.39
    честву
    -0.39
    |()
    -0.38
     Öffentlichkeit
    -0.38
     yoksa
    -0.38
     nationalen
    -0.38
    jangkau
    -0.38
    learn
    -0.38
    POSITIVE LOGITS
     informée
    0.81
     propOrder
    0.79
    parsedMessage
    0.69
    
    0.67
    ScopeManager
    0.60
     CreateTagHelper
    0.59
     surla
    0.59
    ########.
    0.59
    Personensuche
    0.57
    :✨
    0.52
    Activations Density 0.007%

    No Known Activations