© 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-2-9B
    7. Residual Stream - 16k
    9. 35-GEMMASCOPE-RES-16K
    11. 12169
    Prev
    Next
    INDEX
    Explanations

    terms related to health conditions and aspirations for personal improvement or success

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للمعارف
    -0.38
    
    -0.35
     שוליים
    -0.35
     GenerationType
    -0.34
    хьтан
    -0.32
    ừa
    -0.32
    剛剛
    -0.30
    toMatchSnapshot
    -0.30
    مصادر
    -0.30
    Autoritní
    -0.29
    POSITIVE LOGITS
     someday
    2.61
    Someday
    1.91
     sometime
    1.91
     irgendwann
    1.66
     eventually
    1.62
     algún
    1.56
     kiedyś
    1.55
     Sometime
    1.54
    いつか
    1.52
    eventually
    1.46
    Activations Density 0.511%

    No Known Activations