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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 9535
    Prev
    Next
    INDEX
    Explanations

    references to cities and urban environments

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

    the word "City" appearing in various contexts and documents.

    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
    BeginInit
    -0.47
    XmlAccessorType
    -0.46
     resourceCulture
    -0.44
    balleur
    -0.40
    awtextra
    -0.40
     EconPapers
    -0.40
    */),
    -0.40
    InjectAttribute
    -0.39
    SPATH
    -0.38
    equ
    -0.37
    POSITIVE LOGITS
     getCity
    0.84
    City
    0.67
    cityId
    0.66
     City
    0.65
    getCity
    0.65
    cityName
    0.57
     CITY
    0.55
    wide
    0.53
     hall
    0.53
    city
    0.52
    Activations Density 0.116%

    No Known Activations