© 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. 8-GEMMASCOPE-RES-16K
    6. 3321
    Prev
    Next
    INDEX
    Explanations

    geographic features and waterways, particularly those related to the Baltic Sea and its surrounding areas

    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
     
    -0.45
    </blockquote>
    -0.42
     e
    -0.40
    ld
    -0.39
     ע
    -0.39
    std
    -0.38
    arg
    -0.38
    jek
    -0.38
    ikon
    -0.38
    con
    -0.38
    POSITIVE LOGITS
    
    0.80
    RTEE
    0.79
    +#+#
    0.76
    出版年
    0.74
    TintMode
    0.74
    HostException
    0.74
     TextInputType
    0.73
    saraba
    0.72
    URLException
    0.71
    انيف
    0.69
    Activations Density 0.090%

    No Known Activations