© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 16019
    Prev
    Next
    INDEX
    Explanations

    fragments related to language localization and encoding in programming contexts

    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
    RegressionTest
    -0.84
    RenderAtEndOf
    -0.76
    ThroughAttribute
    -0.73
     Administrativna
    -0.68
     AssemblyTitle
    -0.66
     ujednoznacz
    -0.63
    isContained
    -0.63
    bcryptjs
    -0.61
     kasarigan
    -0.61
    NewUrlParser
    -0.61
    POSITIVE LOGITS
    LOCALE
    0.65
    Locale
    0.64
     Locale
    0.61
    locale
    0.58
     language
    0.56
    Language
    0.55
     languages
    0.55
     Language
    0.54
    Languages
    0.54
    language
    0.52
    Activations Density 0.259%

    No Known Activations