Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 4577
    Prev
    Next
    INDEX
    Explanations

    coding-related phrases involving variables and function parameters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betweenstory
    -0.52
     Lat
    -0.49
    ERTE
    -0.47
     ru
    -0.46
     mo
    -0.45
     matched
    -0.45
    Lat
    -0.45
     either
    -0.45
     AssertionError
    -0.44
    moto
    -0.44
    POSITIVE LOGITS
     EconPapers
    0.82
     незавершена
    0.81
    ValueGeneration
    0.72
    archiviato
    0.70
    quelize
    0.69
     purpoſe
    0.67
    Personendaten
    0.67
    Viitteet
    0.66
     שוליים
    0.66
     noten
    0.65
    Activations Density 0.730%

    No Known Activations