© 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. 14-GEMMASCOPE-RES-16K
    11. 6819
    Prev
    Next
    INDEX
    Explanations

    terms related to geographic information systems (GIS) and mapping processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    reportWebVitals
    -0.44
    CardHeader
    -0.40
     jug
    -0.38
     ratio
    -0.38
     JpaRepository
    -0.38
    räge
    -0.38
     initState
    -0.37
    postIndex
    -0.36
     pos
    -0.36
     protein
    -0.36
    POSITIVE LOGITS
     topographic
    0.73
     maps
    0.71
     map
    0.61
     topography
    0.61
     OpenStreetMap
    0.60
     geographic
    0.59
     carto
    0.58
     mapa
    0.58
     mapas
    0.58
     Geographic
    0.57
    Activations Density 0.247%

    No Known Activations