© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 15461
    Prev
    Next
    INDEX
    Explanations

    terms related to translation and language processing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    PreferredItem
    -0.43
     مواليد
    -0.38
     posesión
    -0.38
     للاسماء
    -0.36
    zünd
    -0.35
     tiroirs
    -0.35
     contigo
    -0.35
    يميديا
    -0.35
    rshire
    -0.34
     Reglas
    -0.34
    POSITIVE LOGITS
     translation
    1.07
     translating
    1.01
     translations
    0.96
     translate
    0.94
     translated
    0.92
    translation
    0.91
     Translation
    0.91
     translator
    0.91
    Translation
    0.88
     translators
    0.85
    Activations Density 0.082%

    No Known Activations