© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 13019
    Prev
    Next
    INDEX
    Explanations

    instances of the word "addition" or similar terms indicating an increase or inclusion

    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
     extra
    -0.72
    dafx
    -0.55
     ekstra
    -0.55
    extra
    -0.53
     supplemental
    -0.47
    esticides
    -0.47
     EXTRA
    -0.44
     Magdal
    -0.43
     Extra
    -0.43
     supplementary
    -0.43
    POSITIVE LOGITS
     addition
    2.36
     Addition
    2.27
    addition
    2.23
    Addition
    2.17
     additions
    1.88
     Additions
    1.77
    Additions
    1.50
    Adding
    1.27
     Adding
    1.25
     inclusion
    1.23
    Activations Density 0.151%

    No Known Activations