© 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. 1-GEMMASCOPE-RES-16K
    11. 8641
    Prev
    Next
    INDEX
    Explanations

    names and terms associated with legal cases or characters, particularly those with "Gro" prefixes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    хьтан
    -0.45
    Luft
    -0.42
    öhe
    -0.41
     Kazim
    -0.40
    netinet
    -0.40
     Stande
    -0.39
    seis
    -0.37
     Luft
    -0.36
    ข้าว
    -0.36
    Übernach
    -0.36
    POSITIVE LOGITS
     CreateTagHelper
    0.79
    Gro
    0.77
     gro
    0.73
     Gro
    0.71
    gro
    0.71
     ModelExpression
    0.64
    OrBuilder
    0.62
    mart
    0.61
     GRO
    0.60
     enrolled
    0.59
    Activations Density 0.299%

    No Known Activations