© 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-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 11426
    Prev
    Next
    INDEX
    Explanations

    mentions of locations, buildings, and properties

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

    Real estate, offices, and locations

    np_acts-logits-general · gemini-2.0-flash

    locations for rent or lease

    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
    WriteTagHelper
    -0.54
     cons
    -0.34
    stdbool
    -0.33
    assertj
    -0.33
     zav
    -0.33
    förs
    -0.33
     Cerv
    -0.31
    ngrx
    -0.30
     koh
    -0.30
    Einzelnachweise
    -0.30
    POSITIVE LOGITS
     rented
    0.67
     affitto
    0.61
     leased
    0.59
     locatie
    0.59
     location
    0.58
     lease
    0.58
     Locations
    0.57
     locations
    0.55
     estekak
    0.55
     LOCATIONS
    0.54
    Activations Density 0.156%

    No Known Activations