© 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. 4291
    Prev
    Next
    INDEX
    Explanations

    terms related to pace and thresholds

    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
     Normdatei
    -0.85
     estekak
    -0.66
    Erreferentziak
    -0.62
    تقاوى
    -0.62
     mauva
    -0.62
    bootstrapcdn
    -0.61
     étoit
    -0.61
    +#+#
    -0.59
     beginnetje
    -0.59
    ographia
    -0.58
    POSITIVE LOGITS
    typedef
    0.55
     pace
    0.50
     threshold
    0.49
     showcase
    0.48
     disappointed
    0.48
    showcase
    0.48
     frustrated
    0.47
     milestones
    0.47
     milestone
    0.47
    wp
    0.47
    Activations Density 0.112%

    No Known Activations