© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 14496
    Prev
    Next
    INDEX
    Explanations

    mentions of "capital" in various contexts, such as geographical locations, economic discussions, or financial implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     enfans
    -0.98
     صوتيه
    -0.93
     mijne
    -0.87
     zijne
    -0.82
    AsUp
    -0.82
     mukana
    -0.81
    +#+#
    -0.81
     Italij
    -0.79
     disambiguazione
    -0.79
     estatua
    -0.77
    POSITIVE LOGITS
     capital
    0.89
     Appeal
    0.74
     appeal
    0.66
     
    0.63
     heel
    0.61
     Bro
    0.60
     Capital
    0.60
    .
    0.60
     bro
    0.60
     securities
    0.59
    Activations Density 0.415%

    No Known Activations