© 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. 28-GEMMASCOPE-RES-16K
    11. 4838
    Prev
    Next
    INDEX
    Explanations

    terms related to translation in various contexts

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

    converting languages

    np_acts-logits-general · gemini-2.0-flash

    translate, translation, diagnostic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     initComponents
    -0.40
    idUser
    -0.36
     configureStore
    -0.35
    astéroïdes
    -0.34
    WaitGroup
    -0.34
    RequiresApi
    -0.33
    évaluateur
    -0.33
    CardContent
    -0.32
     createSlice
    -0.32
    utives
    -0.32
    POSITIVE LOGITS
     Translate
    0.72
     translator
    0.71
     translate
    0.68
     translating
    0.66
    Translator
    0.65
    translator
    0.64
     Translator
    0.64
     translation
    0.64
    translation
    0.62
    Translation
    0.62
    Activations Density 0.148%

    No Known Activations