© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 0-GEMMASCOPE-RES-65K
    11. 13662
    Prev
    Next
    INDEX
    Explanations

    terms related to equality and broadcasting, particularly in the context of radio

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     cref
    -0.73
     تضيفلها
    -0.62
     privatization
    -0.61
     guerra
    -0.60
    sizeCache
    -0.60
     kaynağından
    -0.59
    Executives
    -0.58
     bouche
    -0.57
    arques
    -0.56
     wireType
    -0.55
    POSITIVE LOGITS
     Equal
    1.17
     equal
    1.16
     radio
    1.04
    equal
    1.00
    Equal
    0.98
    Radio
    0.94
     EQUAL
    0.93
     Radio
    0.92
    radio
    0.88
     radios
    0.84
    Activations Density 0.057%

    No Known Activations