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

    Neuronpedia

    Jacobian LensNEW
    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. 31-GEMMASCOPE-RES-16K
    11. 5713
    Prev
    Next
    INDEX
    Explanations

    phrases related to English language and multilingual contexts

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

    English language proficiency or English-language content across diverse contexts.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCulture
    -0.42
    migrationBuilder
    -0.39
     Normdatei
    -0.38
     @"/
    -0.36
    featureID
    -0.35
    InstrumentedTest
    -0.34
     chegada
    -0.33
    Бахар
    -0.32
     kupić
    -0.32
     vítima
    -0.32
    POSITIVE LOGITS
     language
    0.89
    speaking
    0.88
     speaking
    0.80
     Language
    0.78
     Speaking
    0.75
    language
    0.74
    Speaking
    0.68
     LANGUAGE
    0.68
    anguage
    0.67
    Language
    0.64
    Activations Density 0.238%

    No Known Activations