© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 7899
    Prev
    Next
    INDEX
    Explanations

    questions and inquiries related to reasoning and explanation

    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
     nahilalakip
    -0.69
     يتيمه
    -0.66
     autorytatywna
    -0.60
    findpost
    -0.58
    Хьажоргаш
    -0.58
     للمعارف
    -0.58
    balleur
    -0.57
     Chwiliwch
    -0.57
    出版年
    -0.56
    
    -0.55
    POSITIVE LOGITS
     so
    2.20
     such
    1.81
    如此
    1.77
     столь
    1.77
    這麼
    1.75
     tantos
    1.73
     tantas
    1.73
     begitu
    1.72
     så
    1.70
    这么
    1.69
    Activations Density 1.133%

    No Known Activations