© 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. MLP Out - 131k
    9. 6-GEMMASCOPE-MLP-131K
    11. 110986
    Prev
    Next
    INDEX
    Explanations

    references to control and power dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-mlp/layer_6/width_131k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.6.hook_mlp_out
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hä
    -0.40
    ้ำ
    -0.40
     control
    -0.36
    prend
    -0.35
     controls
    -0.34
    #+#
    -0.34
     interfacial
    -0.34
     échou
    -0.33
     controlar
    -0.33
     bague
    -0.33
    POSITIVE LOGITS
     AssemblyCompany
    0.65
     NSCoder
    0.64
     utafitiHapana
    0.58
    Hentet
    0.54
     esternos
    0.51
    yntaxException
    0.50
    moveToFirst
    0.49
    RRect
    0.48
     مشين
    0.48
     mxArray
    0.48
    Activations Density 0.003%

    No Known Activations