© 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. 31-GEMMASCOPE-RES-16K
    11. 7720
    Prev
    Next
    INDEX
    Explanations

    references to locations and categories within London

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

    references to London locations and geographical areas.

    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
     oprot
    -0.48
     Youngstown
    -0.46
     Rh
    -0.46
    Rh
    -0.42
     ligiloj
    -0.42
    Ralf
    -0.41
    Elin
    -0.40
    Malawi
    -0.40
     Hilo
    -0.40
    県
    -0.40
    POSITIVE LOGITS
     London
    1.02
    London
    0.98
     Londres
    0.88
    london
    0.87
     LONDON
    0.85
     london
    0.83
     Londra
    0.79
    伦敦
    0.79
     Lond
    0.73
     لندن
    0.73
    Activations Density 0.165%

    No Known Activations