© 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. 33-GEMMASCOPE-RES-16K
    11. 7390
    Prev
    Next
    INDEX
    Explanations

    terms related to specific conditions and behaviors, particularly in the context of medical or scientific discussions

    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
    ATIONAL
    -0.47
    XmlAccessType
    -0.43
    ACIONAL
    -0.41
     Imma
    -0.41
    ational
    -0.41
    httphttps
    -0.39
     Kirkwood
    -0.39
     ligiloj
    -0.39
     propOrder
    -0.39
    ineno
    -0.37
    POSITIVE LOGITS
    sive
    0.96
    tive
    0.94
    IVE
    0.85
    ative
    0.85
    ive
    0.80
     tive
    0.79
    sives
    0.78
    rative
    0.75
    itive
    0.74
    ATIVE
    0.74
    Activations Density 0.360%

    No Known Activations