© 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-2-9B
    4. Residual Stream - 16k
    5. 33-GEMMASCOPE-RES-16K
    6. 8887
    Prev
    Next
    INDEX
    Explanations

    phrases and words related to denial, complexity, and contradiction in discussions or arguments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parsedMessage
    -0.60
    DIPSETTING
    -0.57
    fromnode
    -0.57
    PostInfinity
    -0.56
    setupUi
    -0.51
    uxxxx
    -0.51
    sizeCache
    -0.49
    WireFormatLite
    -0.48
    instein
    -0.48
    contentLoaded
    -0.48
    POSITIVE LOGITS
     fact
    3.81
    fact
    2.92
     Tatsache
    2.84
    Fact
    2.45
     Fact
    2.39
     faptul
    2.27
     hecho
    2.13
     факт
    2.11
     FACT
    2.09
     feit
    2.09
    Activations Density 0.883%

    No Known Activations