© 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-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 939
    Prev
    Next
    INDEX
    Explanations

    terms related to electronic components and their functionalities

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    direction or opposition

    np_acts-logits-general · gemini-2.0-flash

    opposite direction or sign

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    AndEndTag
    -0.60
    zionalità
    -0.56
    delwed
    -0.56
    queryInterface
    -0.55
    VYMaps
    -0.54
    /*
    -0.54
     CURIAM
    -0.54
    tangentMode
    -0.54
     snippetHide
    -0.52
    mobileqq
    -0.50
    POSITIVE LOGITS
     outgoing
    0.71
     outbound
    0.69
     southbound
    0.62
     downward
    0.61
     negative
    0.61
     inbound
    0.59
     northbound
    0.58
     downwards
    0.57
    outbound
    0.57
     positive
    0.56
    Activations Density 1.424%

    No Known Activations