© 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-2-2B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 1590
    Prev
    Next
    INDEX
    Explanations

    technical and scientific terms, particularly in the context of measurements and procedures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 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
    ness
    -0.91
    n
    -0.89
    Personendaten
    -0.79
     Révolution
    -0.77
     ISNI
    -0.75
    d
    -0.75
     chauss
    -0.74
    principalColumn
    -0.69
    dymyr
    -0.69
    nya
    -0.68
    POSITIVE LOGITS
     CIE
    1.20
     CME
    1.16
     ORE
    1.08
    ede
    1.06
     Nore
    1.05
     ATE
    1.04
     SCE
    1.03
     SAGE
    1.02
     Dore
    1.01
    PIE
    1.00
    Activations Density 8.203%

    No Known Activations