© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 10244
    Prev
    Next
    INDEX
    Explanations

    locations and geographical references

    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
     Mem
    -0.75
     Bram
    -0.74
     Swin
    -0.68
    Bram
    -0.66
     Khar
    -0.64
     Alam
    -0.64
    Mem
    -0.63
     PUL
    -0.63
     Marlowe
    -0.62
     Tata
    -0.62
    POSITIVE LOGITS
    QMetaType
    0.98
    ValueStyle
    0.78
     Hokkaido
    0.77
     Sno
    0.74
     Fong
    0.73
    Edmonton
    0.72
     Edmonton
    0.70
     Cuthbert
    0.70
     швей
    0.70
    UnusedPrivate
    0.69
    Activations Density 3.628%

    No Known Activations