© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 15418
    Prev
    Next
    INDEX
    Explanations

    references to locations and affiliations related to Belgium

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RegressionTest
    -0.44
    exitRule
    -0.41
     Pekan
    -0.41
    multicolumn
    -0.40
    </tfoot>
    -0.40
     Alpes
    -0.40
     Kalifor
    -0.39
     LCCN
    -0.39
     viewDidLoad
    -0.38
    CompleteListener
    -0.38
    POSITIVE LOGITS
     Belgian
    0.89
     Belgium
    0.81
    Belgian
    0.76
    Belgium
    0.73
     Flemish
    0.73
     belga
    0.69
     Ghent
    0.69
     Leuven
    0.68
     Belgien
    0.68
     Belgi
    0.67
    Activations Density 0.198%

    No Known Activations