© 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. 3-GEMMASCOPE-RES-16K
    6. 11529
    Prev
    Next
    INDEX
    Explanations

    instances of the word "but" indicating contrast or exception in a discussion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ζω
    -0.59
     Pilate
    -0.58
     otomatig
    -0.58
    scriptcase
    -0.57
    styleUrls
    -0.56
    ampton
    -0.55
     incompatible
    -0.53
     Maia
    -0.52
     curie
    -0.52
     Fland
    -0.52
    POSITIVE LOGITS
    endphp
    0.90
     الاطلاع
    0.69
    EndContext
    0.57
    <bos>
    0.52
    ($__
    0.51
     EconPapers
    0.50
    OutputType
    0.50
    awtextra
    0.50
    ImageIO
    0.49
     disambiguazione
    0.48
    Activations Density 0.240%

    No Known Activations