© 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. 25-GEMMASCOPE-RES-16K
    11. 9763
    Prev
    Next
    INDEX
    Explanations

    technical terms related to surgical procedures and rehabilitation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lui
    -0.77
    herself
    -0.75
    被他
    -0.64
     mnie
    -0.63
    让她
    -0.61
    讓他
    -0.61
     eux
    -0.60
    让他
    -0.59
    跟他
    -0.59
    him
    -0.58
    POSITIVE LOGITS
     there
    2.01
     it
    1.89
     the
    1.37
     we
    1.36
     they
    1.36
     everything
    1.33
     nothing
    1.29
    there
    1.29
     nobody
    1.15
     theres
    1.14
    Activations Density 1.362%

    No Known Activations