© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 843
    Prev
    Next
    INDEX
    Explanations

    references to neighborhoods and their characteristics

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

    about community or residency

    np_acts-logits-general · gemini-2.0-flash

    neighborhoods and residents

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
    <_>
    -0.33
    空港
    -0.33
    TRIBUN
    -0.31
     poursuite
    -0.31
    logi
    -0.31
    CloseOperation
    -0.30
     provinces
    -0.29
    SerializedName
    -0.29
     enterprise
    -0.29
    ensement
    -0.28
    POSITIVE LOGITS
     neighborhood
    0.98
    Residents
    0.97
     residents
    0.94
     Residents
    0.93
    residents
    0.88
     resident
    0.86
    Neighborhood
    0.85
     neighbors
    0.84
    neighborhood
    0.84
     Neighborhood
    0.83
    Activations Density 0.167%

    No Known Activations