© 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. 9-GEMMASCOPE-RES-16K
    11. 16060
    Prev
    Next
    INDEX
    Explanations

    references to various animal species and their conditions in a veterinary context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ConstraintMaker
    -0.48
     desagrad
    -0.47
     AppDelegate
    -0.47
     Rhetor
    -0.46
     régiment
    -0.46
    apunov
    -0.46
     IFTTT
    -0.45
     אתה
    -0.45
     algorit
    -0.45
    исленность
    -0.44
    POSITIVE LOGITS
     category
    0.62
     autorytatywna
    0.60
    IUrlHelper
    0.60
    PyExc
    0.60
    SpringBootTest
    0.59
    IANGLES
    0.59
    
    0.58
    $',
    0.57
     getResources
    0.57
     specialist
    0.56
    Activations Density 0.704%

    No Known Activations