© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 9071
    Prev
    Next
    INDEX
    Explanations

    phrases that express disagreement or doubts about opinions and their significance

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

    "not as" or similar negative comparisons

    np_acts-logits-general · gemini-2.0-flash

    not nearly as much

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     indeed
    -0.64
     بيها
    -0.59
     nonetheless
    -0.47
     любом
    -0.44
    อยู่
    -0.44
    indeed
    -0.43
     jopa
    -0.43
    ftagPool
    -0.43
    aver
    -0.42
    idemiology
    -0.42
    POSITIVE LOGITS
     tão
    1.04
    那麼
    1.00
     tantas
    0.99
     autant
    0.99
     столь
    0.99
     lika
    0.98
    那么
    0.94
     tantos
    0.92
     tanta
    0.88
     толкова
    0.88
    Activations Density 0.353%

    No Known Activations