© 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. 9-GEMMASCOPE-RES-16K
    11. 12242
    Prev
    Next
    INDEX
    Explanations

    references to individuals and groups of people in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     asegurar
    -0.44
     matéria
    -0.42
     corregir
    -0.41
     olvidar
    -0.41
     asegurarse
    -0.40
     allzu
    -0.39
     diğer
    -0.38
     bütün
    -0.38
     prestasi
    -0.38
     extraer
    -0.38
    POSITIVE LOGITS
     persons
    1.24
     Persons
    1.17
     person
    1.15
     people
    1.13
     perfons
    1.09
    persons
    1.07
    Persons
    1.05
     Person
    1.05
    people
    1.05
     personen
    1.02
    Activations Density 0.548%

    No Known Activations