© 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. 25-GEMMASCOPE-RES-16K
    11. 12645
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to astronomical or physical concepts, particularly involving matter and distributions within galaxies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Chinese
    -1.67
     China
    -1.58
     Beijing
    -1.46
    Chinese
    -1.45
     CHINESE
    -1.44
    China
    -1.41
     Shanghai
    -1.41
     chinese
    -1.41
     CHINA
    -1.40
     китай
    -1.35
    POSITIVE LOGITS
    Autoritní
    0.49
     Morelos
    0.47
    onedDateTime
    0.47
     Indy
    0.47
     Idaho
    0.47
     Tristan
    0.45
     Barbados
    0.44
     Arag
    0.44
    getRepository
    0.43
    Indy
    0.43
    Activations Density 1.523%

    No Known Activations