© 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. 3-GEMMASCOPE-RES-16K
    11. 5207
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "Community" and related terms associated with family 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
     erſt
    -0.86
     laſſen
    -0.85
     müſſen
    -0.85
     Waſſer
    -0.84
     ſelbſt
    -0.83
     vooz
    -0.83
     ſoll
    -0.82
     dieſe
    -0.82
    ésultats
    -0.81
    ſammen
    -0.80
    POSITIVE LOGITS
     Family
    1.30
     Community
    1.21
    Family
    1.05
    Community
    0.91
     Friends
    0.60
     FAMILY
    0.59
     Comunidad
    0.57
     Self
    0.54
     Família
    0.52
    Self
    0.48
    Activations Density 0.170%

    No Known Activations