© 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. 0-GEMMASCOPE-RES-16K
    11. 259
    Prev
    Next
    INDEX
    Explanations

    terms related to electrical or electromechanical concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sizeCache
    -0.49
     vPvB
    -0.40
    askar
    -0.36
    WaitGroup
    -0.36
     Infórmanos
    -0.36
    BeginInit
    -0.35
    farin
    -0.34
    InitVars
    -0.34
    mẫu
    -0.34
    Graham
    -0.33
    POSITIVE LOGITS
     elect
    3.23
     electro
    3.20
     Elect
    3.08
     Electro
    2.97
    Elect
    2.94
    elect
    2.89
    Electro
    2.86
    ELECT
    2.83
     electric
    2.78
    electro
    2.78
    Activations Density 0.171%

    No Known Activations