© 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. 1-GEMMASCOPE-RES-16K
    11. 7252
    Prev
    Next
    INDEX
    Explanations

    conjunctions and prepositions used in specific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AsUp
    -1.01
     beginnetje
    -0.91
     Мексичка
    -0.81
    InstrumentedTest
    -0.80
    Rüyada
    -0.80
    colgroup
    -0.79
    دانشنامهٔ
    -0.78
    transQ
    -0.76
    prüche
    -0.76
    astéro
    -0.76
    POSITIVE LOGITS
     example
    0.73
     examples
    0.72
     przykład
    0.67
     esempio
    0.65
     exemples
    0.64
     ejemplo
    0.61
     instance
    0.61
     exemple
    0.60
     ejemplos
    0.60
    examples
    0.59
    Activations Density 0.219%

    No Known Activations