© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 37-GEMMASCOPE-RES-16K
    11. 3832
    Prev
    Next
    INDEX
    Explanations

    references to urban development and urban environments

    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
     autorytatywna
    -0.68
    tvguidetime
    -0.67
    лтамалар
    -0.62
    postIndex
    -0.59
    Bronnen
    -0.57
    ImageContext
    -0.54
     GenerationType
    -0.52
    turnstile
    -0.50
     Wikimedijinoj
    -0.50
    Personendaten
    -0.49
    POSITIVE LOGITS
    ity
    0.58
    ites
    0.48
     dwellers
    0.48
     renewal
    0.45
    ized
    0.45
    /**
    0.45
    Życiorys
    0.44
    isation
    0.44
    ite
    0.43
     dwell
    0.42
    Activations Density 0.161%

    No Known Activations