© 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-2-9B
    4. Residual Stream - 16k
    5. 36-GEMMASCOPE-RES-16K
    6. 8202
    Prev
    Next
    INDEX
    Explanations

    various forms of the word "education" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/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.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     education
    -0.50
     educativa
    -0.40
     createSlice
    -0.39
     Metacritic
    -0.39
     éducation
    -0.39
     educated
    -0.39
     Bundy
    -0.38
     Pila
    -0.38
     EDUCATION
    -0.38
     pendidikan
    -0.38
    POSITIVE LOGITS
    ally
    0.55
     attainment
    0.54
    institution
    0.50
    تقاوى
    0.50
     CreateTagHelper
    0.48
     poveznice
    0.47
     institutions
    0.47
     institution
    0.47
    Institution
    0.46
     Institutions
    0.46
    Activations Density 0.051%

    No Known Activations