© 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. 33-GEMMASCOPE-RES-16K
    11. 12272
    Prev
    Next
    INDEX
    Explanations

    details related to locations, particularly cities and diplomatic entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Harz
    -0.33
    getattr
    -0.31
    cestershire
    -0.30
    fwrite
    -0.29
     Мол
    -0.27
     Landkreis
    -0.27
    Namespace
    -0.27
    atorship
    -0.26
    borderBottom
    -0.26
     Bergmann
    -0.26
    POSITIVE LOGITS
     London
    1.47
     Bangkok
    1.40
     Toronto
    1.39
     Tokyo
    1.35
     Jakarta
    1.34
     Seoul
    1.33
     Dublin
    1.32
     Beijing
    1.31
     Mumbai
    1.28
     Manila
    1.28
    Activations Density 1.021%

    No Known Activations