© 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. 6231
    Prev
    Next
    INDEX
    Explanations

    references to individuals or groups living in a specific area or community

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

    "resident" or "residents"

    np_acts-logits-general · gemini-2.0-flash

    resident of

    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
    omock
    -0.59
    <bos>
    -0.58
     مرئيه
    -0.56
    Egypte
    -0.56
     Catawiki
    -0.55
    posedge
    -0.54
    tableFuture
    -0.53
    taylor
    -0.53
    riceps
    -0.52
    formKey
    -0.52
    POSITIVE LOGITS
     resident
    1.01
     residents
    0.91
     Resident
    0.88
    Resident
    0.87
     inhabitant
    0.86
     Residents
    0.83
     Residence
    0.81
     residence
    0.81
    Residents
    0.78
     Bewohner
    0.77
    Activations Density 0.183%

    No Known Activations