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. 122698
    Prev
    Next
    INDEX
    Explanations

    programming commands and constructs related to exiting or navigating back in a software context

    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
     限
    -0.27
    NSDictionary
    -0.27
     following
    -0.26
     Stimme
    -0.26
     hacerse
    -0.26
     Storm
    -0.25
     स्था
    -0.24
    限
    -0.24
     Schreiber
    -0.24
     indican
    -0.24
    POSITIVE LOGITS
    parsedMessage
    0.83
     EconPapers
    0.75
     OFDb
    0.74
     betweenstory
    0.73
    featureID
    0.68
    awtextra
    0.67
    fromnode
    0.66
    EDEFAULT
    0.65
    InitVars
    0.63
     nahilalakip
    0.61
    Activations Density 0.002%

    No Known Activations