© 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. 15983
    Prev
    Next
    INDEX
    Explanations

    references to terminal devices or connectivity in technical contexts

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    पया
    -0.42
    把
    -0.35
     Main
    -0.35
    Main
    -0.32
     estim
    -0.32
     lệ
    -0.31
     ис
    -0.31
    TAWA
    -0.31
     desen
    -0.30
    Please
    -0.30
    POSITIVE LOGITS
     Terminal
    0.85
     terminal
    0.79
    Terminal
    0.77
     Bonds
    0.71
     Fragment
    0.69
    Fragment
    0.68
    LabelTagHelper
    0.68
     bonds
    0.66
     Bond
    0.65
     Terminals
    0.65
    Activations Density 0.306%

    No Known Activations