© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 37-GEMMASCOPE-RES-16K
    11. 659
    Prev
    Next
    INDEX
    Explanations

    concepts related to diversity and variety, particularly in the context of beliefs, cultures, and species

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ьаж
    -0.53
    Хьажоргаш
    -0.49
     يتيمه
    -0.45
    Solución
    -0.40
    providedIn
    -0.40
     Mockito
    -0.36
    cyd
    -0.36
    arpur
    -0.36
    clusal
    -0.36
    нави
    -0.35
    POSITIVE LOGITS
     diversity
    2.67
     varied
    2.50
     diverse
    2.47
     variety
    2.45
    diverse
    2.27
     diversified
    2.25
     diversité
    2.23
    Diverse
    2.20
     diversidad
    2.17
    diversity
    2.16
    Activations Density 1.320%

    No Known Activations