© 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. 1-GEMMASCOPE-RES-16K
    11. 6495
    Prev
    Next
    INDEX
    Explanations

    references to towers and tower structures in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyProduct
    -0.73
     fieldNum
    -0.69
    IInterface
    -0.69
     nahilalakip
    -0.68
    FormBorderStyle
    -0.62
    scryfall
    -0.62
     typelib
    -0.61
    AntiForgeryToken
    -0.61
    imageshack
    -0.60
    JspWriter
    -0.60
    POSITIVE LOGITS
    ato
    0.89
    hes
    0.86
     Tall
    0.74
    ATO
    0.73
     collapses
    0.70
     deliberate
    0.69
     tal
    0.69
     Tal
    0.67
     collapsed
    0.67
     tall
    0.66
    Activations Density 0.045%

    No Known Activations