© 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. 110977
    Prev
    Next
    INDEX
    Explanations

    terms related to disassembly and dismantling processes

    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
     dismantle
    -1.28
     dismantled
    -1.27
     dismantling
    -1.25
     dismant
    -1.09
     disassembled
    -1.04
     disassemble
    -0.96
     disassembly
    -0.84
     Dism
    -0.73
    拆
    -0.71
     disbanded
    -0.56
    POSITIVE LOGITS
     arşivlendi
    0.55
    tagPool
    0.46
    adpleegd
    0.44
     OMITBAD
    0.44
     kasarigan
    0.43
     titolata
    0.43
    Biografi
    0.42
    ViewFeatures
    0.40
    Referințe
    0.39
     umani
    0.39
    Activations Density 0.002%

    No Known Activations