© 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
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 12722
    Prev
    Next
    INDEX
    Explanations

    references to cities and locations

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

    geographic locations and place names being described in travel or informational contexts.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     <<<<<<<<<<<<<<
    -0.68
     estekak
    -0.64
    XmlAccessorType
    -0.60
     חיצוניים
    -0.58
    EndInit
    -0.58
     resourceCulture
    -0.57
    PageRoute
    -0.57
    ConfigureAwait
    -0.57
    XmlAccessType
    -0.56
    BASEPATH
    -0.56
    POSITIVE LOGITS
     city
    1.51
     cities
    1.27
     town
    1.27
     città
    1.12
    city
    1.09
     ciudad
    1.09
     towns
    1.07
     capital
    1.07
     cidade
    1.02
     City
    1.00
    Activations Density 0.308%

    No Known Activations