© 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. 16-GEMMASCOPE-RES-16K
    11. 5465
    Prev
    Next
    INDEX
    Explanations

    transitional phrases and contrasting language

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

    that indicate contrast or concession

    np_acts-logits-general · gemini-2.0-flash

    contrast words introducing positive outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hésite
    -0.78
     Assyrian
    -0.73
    GIH
    -0.70
    AlterField
    -0.69
    InvalidProtocol
    -0.69
     Whigs
    -0.68
     unmarked
    -0.67
     unbelie
    -0.67
     muna
    -0.66
    APOLIS
    -0.65
    POSITIVE LOGITS
     nevertheless
    1.01
     зато
    0.94
     nonetheless
    0.90
     Nevertheless
    0.78
    Nevertheless
    0.75
     dennoch
    0.73
    Nonetheless
    0.72
     fortunately
    0.71
    それでも
    0.70
    好在
    0.69
    Activations Density 0.335%

    No Known Activations