© 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. 2-GEMMASCOPE-RES-16K
    11. 8452
    Prev
    Next
    INDEX
    Explanations

    repeated use of the word "that" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    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
    -0.46
    __(/*!
    -0.39
    adaptiveStyles
    -0.38
    Rüyada
    -0.37
    recated
    -0.36
    لينكات
    -0.36
    erto
    -0.35
     cli
    -0.35
    Slf
    -0.35
    /*
    -0.35
    POSITIVE LOGITS
     That
    1.52
     THAT
    1.45
    That
    1.45
     those
    1.41
    THAT
    1.28
    Those
    1.25
     Those
    1.24
    those
    1.23
     THOSE
    1.23
     daquele
    1.13
    Activations Density 0.246%

    No Known Activations