© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 104772
    Prev
    Next
    INDEX
    Explanations

    instances of the term "join" in various contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    MemoryWarning
    -0.78
     المعيارى
    -0.73
     canst
    -0.69
    tvguidetime
    -0.69
     statusCode
    -0.68
    ScreenState
    -0.65
    BrowserModule
    -0.63
     BrowserModule
    -0.63
     ControllerBase
    -0.62
     nervosa
    -0.62
    POSITIVE LOGITS
    join
    0.90
     Join
    0.78
    Join
    0.76
    JOIN
    0.74
     join
    0.72
     JOIN
    0.71
    joins
    0.66
     joins
    0.65
     Joining
    0.59
     joined
    0.56
    Activations Density 0.007%

    No Known Activations