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

    Neuronpedia

    Jacobian LensNEW
    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. 3-GEMMASCOPE-RES-16K
    11. 4745
    Prev
    Next
    INDEX
    Explanations

    instances of the term "load."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    */].
    -0.42
     CommonModule
    -0.40
     Paglinawan
    -0.34
     namorado
    -0.34
     onlyOwner
    -0.33
    ümmer
    -0.33
    ũng
    -0.32
    xxxxxxxxxxxxxxxx
    -0.31
     Aven
    -0.31
    DIPSETTING
    -0.31
    POSITIVE LOGITS
     load
    4.03
     Load
    3.64
    load
    3.36
    Load
    3.34
     LOAD
    3.14
     loads
    3.08
     Loads
    2.95
    LOAD
    2.80
    Loads
    2.67
    loads
    2.61
    Activations Density 0.068%

    No Known Activations