© 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. 2-GEMMASCOPE-RES-16K
    11. 12636
    Prev
    Next
    INDEX
    Explanations

    instances of the word "join" and its variations in different contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     canst
    -0.47
    fortawesome
    -0.44
    phazard
    -0.43
     незавершена
    -0.40
     MutableLiveData
    -0.39
    didSet
    -0.39
     Rotterdam
    -0.38
     Verona
    -0.38
     kohdetta
    -0.37
    Errorf
    -0.36
    POSITIVE LOGITS
     join
    4.03
     joining
    3.75
     Join
    3.61
    join
    3.56
     joins
    3.53
    Join
    3.50
     Joining
    3.42
     joined
    3.36
     JOIN
    3.27
    Joining
    3.25
    Activations Density 0.146%

    No Known Activations