© 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-2-2B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 1930
    Prev
    Next
    INDEX
    Explanations

    references to specific chemical compounds or substances, particularly in a scientific context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CloseOperation
    -1.03
    PerformLayout
    -0.85
     EconPapers
    -0.84
    AddAttribute
    -0.83
     OFDb
    -0.77
     &___
    -0.77
    ArgsConstructor
    -0.74
    EndInit
    -0.71
    aarrggbb
    -0.68
    bledon
    -0.67
    POSITIVE LOGITS
     Bux
    1.07
    xes
    1.06
    Rox
    0.93
    Gx
    0.92
     Pax
    0.91
     vox
    0.90
    LAX
    0.89
     Dux
    0.89
    kx
    0.88
     pax
    0.88
    Activations Density 0.763%

    No Known Activations