© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 8872
    Prev
    Next
    INDEX
    Explanations

    numerical values and measurements, particularly fractions and quantities related to time or other units

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/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.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Orrell
    -0.77
    es
    -0.76
     def
    -0.73
    /
    -0.69
    )
    -0.67
    def
    -0.64
     «
    -0.64
    ly
    -0.62
    ()}>
    -0.62
    hline
    -0.62
    POSITIVE LOGITS
     eighty
    1.11
     seventy
    1.08
     sixty
    1.06
     ninety
    1.05
    WEBPACK
    1.00
     Ninety
    0.98
     forty
    0.97
     fifty
    0.97
     nineteen
    0.97
     thirty
    0.96
    Activations Density 0.119%

    No Known Activations