© 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. 20-GEMMASCOPE-RES-16K
    6. 13291
    Prev
    Next
    INDEX
    Explanations

    phrases related to civic engagement and community health issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    references to neighborhoods and local community life—residents, neighbors, civic associations, and community meetings/initiatives.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    references to local community organizations, neighborhood groups, and civic associations.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    logi
    -0.32
    <_>
    -0.31
    TRIBUN
    -0.30
     provinces
    -0.30
     poursuite
    -0.30
    სქოლიო
    -0.27
    空港
    -0.26
     provinsi
    -0.26
     huel
    -0.25
     определя
    -0.25
    POSITIVE LOGITS
     neighborhood
    1.03
    Residents
    0.96
     residents
    0.96
     Residents
    0.93
    residents
    0.92
    neighborhood
    0.91
     Neighborhood
    0.88
     neighbors
    0.88
     resident
    0.87
    Neighborhood
    0.87
    Activations Density 0.124%

    No Known Activations