© 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-2-2B
    7. Residual Stream - 16k
    9. 8-GEMMASCOPE-RES-16K
    11. 10079
    Prev
    Next
    INDEX
    Explanations

    the word "besides" and its variations, indicating the neuron is looking for additional information or context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Str
    -0.67
    mayr
    -0.58
    ruvate
    -0.57
    TouchListener
    -0.57
    capp
    -0.57
    Cyto
    -0.56
    brum
    -0.56
    feinander
    -0.55
     apparaat
    -0.54
    Str
    -0.54
    POSITIVE LOGITS
    besides
    1.16
     besides
    1.14
    Besides
    1.10
     Besides
    1.03
     defaultstate
    1.02
     Oltre
    1.01
    enumi
    1.00
    Selain
    0.96
    mybatisplus
    0.95
     Além
    0.95
    Activations Density 0.098%

    No Known Activations