© 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-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 5548
    Prev
    Next
    INDEX
    Explanations

    proper nouns and specific references, particularly related to individuals and institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    й
    -0.94
     Bartol
    -0.89
    一个
    -0.89
     manufact
    -0.89
    __*/
    -0.89
    Gott
    -0.87
    IIIIIIII
    -0.82
    йки
    -0.82
     Baldwin
    -0.81
     Sapi
    -0.81
    POSITIVE LOGITS
     soeur
    0.95
    に
    0.93
     nationaux
    0.92
     suivie
    0.88
    ab
    0.85
     Lynd
    0.84
    ly
    0.83
    ag
    0.82
     sabbia
    0.82
     moeite
    0.79
    Activations Density 2.158%

    No Known Activations