© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 107549
    Prev
    Next
    INDEX
    Explanations

    instances of asynchronous programming patterns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
     ujednoznacz
    -0.77
    Tikang
    -0.70
    ViewFeatures
    -0.68
    delwed
    -0.68
    MockBean
    -0.65
    SharedDtor
    -0.64
     queſta
    -0.64
     surla
    -0.63
    verwijspagina
    -0.63
    rungsseite
    -0.63
    POSITIVE LOGITS
    DispatchQueue
    0.57
    Schedulers
    0.38
     חש
    0.34
     darling
    0.33
    reactivex
    0.33
     Darling
    0.32
     opportune
    0.31
    Dispatchers
    0.31
    chy
    0.31
     delayed
    0.31
    Activations Density 0.002%

    No Known Activations