© 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. 108325
    Prev
    Next
    INDEX
    Explanations

    references to latching mechanisms and circuits

    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
     latch
    -1.81
     Latch
    -1.53
    latch
    -1.45
    Latch
    -1.43
     lat
    -0.92
    sizeCache
    -0.83
     pinulongan
    -0.83
     resourceCulture
    -0.74
    Lat
    -0.71
    tagHelperRunner
    -0.69
    POSITIVE LOGITS
     mas
    0.29
     mast
    0.28
    Quic
    0.28
    itemBuilder
    0.27
    Rotate
    0.27
    MigrationBuilder
    0.27
    Distribu
    0.26
    gp
    0.25
     Brodie
    0.24
    一
    0.24
    Activations Density 0.002%

    No Known Activations