© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 7058
    Prev
    Next
    INDEX
    Explanations

    references to zoning laws and property regulations

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

    land, lots, or parcels

    np_acts-logits-general · gemini-2.0-flash

    land, lots, parcels, acreage, property

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 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
     focused
    -0.30
     indoc
    -0.29
    IonicModule
    -0.28
     pico
    -0.27
     output
    -0.27
     zeit
    -0.26
     народ
    -0.25
     yogurt
    -0.25
     genre
    -0.25
     rik
    -0.25
    POSITIVE LOGITS
     landowners
    1.05
     land
    0.99
     landowner
    0.95
     Grundstück
    0.92
    DockStyle
    0.90
     acreage
    0.90
     property
    0.87
     acres
    0.84
     parcels
    0.82
     propietarios
    0.82
    Activations Density 0.384%

    No Known Activations