© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 15651
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to locations and notable institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ReusableCell
    -0.92
    +#+#
    -0.89
    GEBURTSDATUM
    -0.87
    LLocation
    -0.85
     estimés
    -0.83
     comets
    -0.77
     Ciro
    -0.77
     Quanto
    -0.77
     BRIT
    -0.76
     Sardin
    -0.75
    POSITIVE LOGITS
     setOpen
    0.91
    THESIS
    0.85
     Varela
    0.79
     Hecht
    0.75
    Mbps
    0.74
     Joyce
    0.72
    CURY
    0.71
     Toro
    0.70
     Bergman
    0.70
    Mucha
    0.69
    Activations Density 3.338%

    No Known Activations