© 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-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 2026
    Prev
    Next
    INDEX
    Explanations

    elements related to mobile tracking applications and their features

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

    position, location, and coordinates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     resourceCulture
    -0.59
    IsMutable
    -0.55
    енча
    -0.54
     createSlice
    -0.54
    jmniej
    -0.52
    afficheront
    -0.52
    новниш
    -0.52
    ỡng
    -0.51
     يتيمه
    -0.49
    ictwa
    -0.49
    POSITIVE LOGITS
     coordinates
    1.78
     location
    1.59
     Coordinates
    1.55
     Location
    1.41
    coordinates
    1.41
     coordinate
    1.40
    Coordinates
    1.35
     coords
    1.33
     LOCATION
    1.33
    location
    1.33
    Activations Density 0.291%

    No Known Activations