© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 12803
    Prev
    Next
    INDEX
    Explanations

    references to online learning and remote engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CROSSTALK
    -0.29
     contre
    -0.29
     jeter
    -0.29
     stop
    -0.28
     dispara
    -0.28
    UNCIL
    -0.28
    CppMethod
    -0.27
    ValueGenerated
    -0.27
     Stop
    -0.26
     stops
    -0.26
    POSITIVE LOGITS
     remote
    1.00
    remote
    0.94
    Remote
    0.88
    远程
    0.86
     Remote
    0.86
     remotely
    0.85
     дистан
    0.84
     REMOTE
    0.82
    REMOTE
    0.78
     remota
    0.77
    Activations Density 0.380%

    No Known Activations