© 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-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 3862
    Prev
    Next
    INDEX
    Explanations

    references to geographic locations and properties related to real estate

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

    Property names (e.g., Cedar Grove, Sunset High)

    np_acts-logits-general · gemini-2.0-flash

    Cedar Grove

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Datuak
    -0.52
    Demografie
    -0.47
     personnalité
    -0.45
    تفصیلات
    -0.44
     typelib
    -0.44
    protoimpl
    -0.44
     Dummies
    -0.44
    WireFormat
    -0.44
    KommentareTeilen
    -0.44
     <>",
    -0.44
    POSITIVE LOGITS
     Hills
    0.97
     Valley
    0.97
     Heights
    0.94
     Ridge
    0.90
     Hill
    0.90
     Grove
    0.88
    Hills
    0.88
    Valley
    0.85
     Pointe
    0.85
     Point
    0.84
    Activations Density 0.366%

    No Known Activations