© 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. 37-GEMMASCOPE-RES-16K
    11. 7911
    Prev
    Next
    INDEX
    Explanations

    elements related to cultural identity and nostalgia

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyVersion
    -0.44
     humanidade
    -0.39
     Übungen
    -0.39
     objed
    -0.37
    Soorten
    -0.35
     desmon
    -0.35
    verlauf
    -0.33
    magitan
    -0.33
     inneces
    -0.33
     coussin
    -0.33
    POSITIVE LOGITS
     geographically
    1.18
     geographical
    1.00
     suburbs
    0.98
     geography
    0.96
     locals
    0.94
     geographic
    0.94
     suburb
    0.91
     cosmopolitan
    0.89
     cities
    0.89
     commute
    0.88
    Activations Density 0.475%

    No Known Activations