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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 4688
    Prev
    Next
    INDEX
    Explanations

    mentions of different languages and their translations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    mentions of languages and specific language names.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    AddTagHelper
    -0.69
    UrlResolution
    -0.68
     EconPapers
    -0.63
    ValueStyle
    -0.61
    RenderAtEndOf
    -0.60
    makeConstraints
    -0.58
    UnusedPrivate
    -0.58
    ChildScrollView
    -0.56
    AlterField
    -0.55
    MemoryWarning
    -0.54
    POSITIVE LOGITS
     language
    0.74
     Language
    0.66
     languages
    0.64
    language
    0.63
    Language
    0.60
     Languages
    0.52
    English
    0.52
     idioma
    0.51
     Arabic
    0.50
     English
    0.49
    Activations Density 0.140%

    No Known Activations