© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 23-GEMMASCOPE-RES-16K
    11. 1311
    Prev
    Next
    INDEX
    Explanations

    references to water enhancement and related scientific initiatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/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.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disponibilités
    -0.39
     fark
    -0.38
     Kalamazoo
    -0.36
    ือก
    -0.35
    Hochspringen
    -0.34
    PYX
    -0.33
    回
    -0.33
     Asheville
    -0.33
     Bohemia
    -0.33
    发表于
    -0.33
    POSITIVE LOGITS
     Dubai
    1.02
    Dubai
    0.91
     Dhabi
    0.88
     dubai
    0.85
     Saudi
    0.83
     UAE
    0.82
     Qatar
    0.82
    dubai
    0.80
     Kuwait
    0.79
     Sharjah
    0.76
    Activations Density 0.076%

    No Known Activations