© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 6349
    Prev
    Next
    INDEX
    Explanations

    phrases that initiate contradictory or contrasting statements

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

    Sentences starting with "But"

    np_acts-logits-general · gemini-2.0-flash

    But

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mengen
    -0.46
    iloj
    -0.45
    GeneratedMessage
    -0.40
     للاسماء
    -0.40
     članak
    -0.40
    webElement
    -0.39
    por
    -0.36
    matchCondition
    -0.35
     manualidades
    -0.35
     ویکی‌پدی
    -0.35
    POSITIVE LOGITS
    But
    0.97
     But
    0.90
    MLLoader
    0.63
     CreateTagHelper
    0.63
    BUT
    0.62
    Хьажоргаш
    0.60
    Pero
    0.56
     andererseits
    0.56
     BUT
    0.55
     Pero
    0.54
    Activations Density 0.294%

    No Known Activations