Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 5531
    Prev
    Next
    INDEX
    Explanations

    references to translation in programming or documentation contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ########.
    -0.81
    DockStyle
    -0.81
    setupUi
    -0.80
    windowFixed
    -0.76
    IsMutable
    -0.76
     yym
    -0.76
     ***!
    -0.70
     nakalista
    -0.68
    bootstrapcdn
    -0.67
    zzleHttp
    -0.66
    POSITIVE LOGITS
    translation
    1.77
     translation
    1.09
    Translation
    1.00
     Translation
    0.96
    translations
    0.78
     translations
    0.77
     TRANSLATION
    0.73
     translated
    0.73
     translate
    0.71
    translated
    0.66
    Activations Density 0.013%

    No Known Activations