© 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. 3-GEMMASCOPE-RES-16K
    11. 5707
    Prev
    Next
    INDEX
    Explanations

    quotes or direct speech

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -0.46
     pungkas
    -0.40
    Weiterlesen
    -0.40
    źródło
    -0.39
    Tembelea
    -0.39
     Rücksicht
    -0.38
     pungkasnya
    -0.38
    Citiți
    -0.37
     Мексичка
    -0.37
     Zustimmung
    -0.36
    POSITIVE LOGITS
    出版年
    0.51
     Morpho
    0.47
     Xs
    0.46
    Ќ
    0.45
     Ys
    0.45
    Eig
    0.44
     Ive
    0.44
    wouldn
    0.43
     IDs
    0.43
    hobby
    0.43
    Activations Density 0.280%

    No Known Activations