© 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. 24-GEMMASCOPE-RES-16K
    11. 2130
    Prev
    Next
    INDEX
    Explanations

    linguistic skills and experience in translation, particularly in multiple languages

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

    translation between languages

    np_acts-logits-general · gemini-2.0-flash

    translation, translated language

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     MainAxisSize
    -0.79
    DockStyle
    -0.70
    +#+#
    -0.68
    Życiorys
    -0.64
    MeasureSpec
    -0.59
    ConstraintMaker
    -0.52
     Payton
    -0.51
    ArrowToggle
    -0.51
     tartalomajánló
    -0.51
    Xna
    -0.51
    POSITIVE LOGITS
     translation
    2.21
     translations
    1.93
     translating
    1.88
     Translation
    1.84
     translated
    1.80
     translate
    1.78
    translation
    1.75
     translators
    1.74
     translator
    1.73
    Translation
    1.67
    Activations Density 0.226%

    No Known Activations