© 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-2-2B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 7187
    Prev
    Next
    INDEX
    Explanations

    references to communication, particularly in a technological or teamwork context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 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
    GenerationType
    -0.81
     Xunit
    -0.74
     estimés
    -0.72
    roek
    -0.70
    äksi
    -0.69
     Normdatei
    -0.67
     viewType
    -0.65
     plomb
    -0.64
     Pasha
    -0.63
    ïsme
    -0.62
    POSITIVE LOGITS
     communication
    1.70
     communications
    1.61
     communic
    1.57
     communicating
    1.52
     COMMUNIC
    1.51
     Communication
    1.45
     communicate
    1.43
     Communic
    1.43
     communicative
    1.42
    Commun
    1.41
    Activations Density 0.059%

    No Known Activations