© 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. 8-GEMMASCOPE-RES-16K
    11. 11898
    Prev
    Next
    INDEX
    Explanations

    chemical compounds and their interactions, particularly focusing on sulfides, metal complexes, and their effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     whiteness
    -0.74
    EndContext
    -0.71
     Ruk
    -0.70
    ChildScrollView
    -0.69
     chup
    -0.63
    webElementXpaths
    -0.61
     bry
    -0.60
     NgModule
    -0.60
     mosquitoes
    -0.59
    UnifiedTopology
    -0.59
    POSITIVE LOGITS
    queryInterface
    0.77
     黑色
    0.61
     خارجية
    0.61
    Persön
    0.60
     Argus
    0.59
    黑色
    0.56
     متعلقه
    0.56
     Dowling
    0.55
     Seelen
    0.54
    otonin
    0.53
    Activations Density 1.141%

    No Known Activations