© 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
    7. Residual Stream - 16k
    9. 35-GEMMASCOPE-RES-16K
    11. 12360
    Prev
    Next
    INDEX
    Explanations

    phrases indicating contradiction or complexity in a narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    setupUi
    -0.54
    parsedMessage
    -0.54
    TypedDataSet
    -0.52
    EndInit
    -0.50
     Offisielt
    -0.48
    principalTable
    -0.48
     detailsNormal
    -0.47
    fromnode
    -0.47
     Arteta
    -0.47
     auffi
    -0.47
    POSITIVE LOGITS
     fact
    2.69
     Tatsache
    1.90
    fact
    1.82
     faptul
    1.73
     idea
    1.50
     hecho
    1.50
     feit
    1.39
     fatto
    1.36
    Fact
    1.35
     possibility
    1.34
    Activations Density 1.011%

    No Known Activations