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

    Neuronpedia

    Jacobian LensNEW
    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. 3-GEMMASCOPE-RES-16K
    11. 4917
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to various forms of "pro" or "professional" terminology in medical and scientific contexts

    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
    RenderAtEndOf
    -0.58
     насељу
    -0.54
    ceğine
    -0.46
    PerformLayout
    -0.46
     EconPapers
    -0.45
    цездатний
    -0.44
     noDo
    -0.43
    TintMode
    -0.43
    期刊论文
    -0.43
    Rüyada
    -0.42
    POSITIVE LOGITS
     PRO
    1.79
     Pro
    1.76
    pro
    1.76
    Pro
    1.74
     pro
    1.73
    PRO
    1.72
     프로
    1.40
    про
    1.37
     про
    1.36
     Про
    1.36
    Activations Density 1.103%

    No Known Activations