© 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. 6322
    Prev
    Next
    INDEX
    Explanations

    references to bacterial toxins and pathogens

    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
     Bouch
    -0.69
     ACE
    -0.64
     Haller
    -0.62
     Cress
    -0.59
     RPA
    -0.59
     Bonner
    -0.58
     Pera
    -0.57
     Boucher
    -0.56
     Robson
    -0.53
     Bouchard
    -0.52
    POSITIVE LOGITS
     Shi
    3.29
    Shi
    3.18
     shi
    2.82
    shi
    2.64
    SHI
    1.92
     shifter
    1.92
     Shields
    1.77
     Shih
    1.74
    Shir
    1.73
     Shia
    1.71
    Activations Density 0.437%

    No Known Activations