© 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. 7-GEMMASCOPE-RES-16K
    11. 3183
    Prev
    Next
    INDEX
    Explanations

    references to caves and underground environments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     doPost
    -0.50
    ItemStack
    -0.40
     os
    -0.39
    ~
    -0.39
    WebServlet
    -0.38
     stator
    -0.38
    спор
    -0.38
    raw
    -0.37
     aos
    -0.37
    gisi
    -0.36
    POSITIVE LOGITS
     underground
    0.80
     InputDecoration
    0.78
     subterrá
    0.76
     caves
    0.75
     disponibilités
    0.75
     cavern
    0.75
     iNdEx
    0.73
    Underground
    0.72
     Underground
    0.72
     surla
    0.72
    Activations Density 0.233%

    No Known Activations