© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. MLP Out - 131k
    5. 6-GEMMASCOPE-MLP-131K
    6. 108903
    Prev
    Next
    INDEX
    Explanations

    negative sentiments related to chaos or disorganization

    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
     messed
    -1.45
     fucked
    -1.16
     screwed
    -0.93
     ProtoMessage
    -0.77
     ruined
    -0.74
     المعيارى
    -0.73
     defaultstate
    -0.73
     messing
    -0.73
    aarrggbb
    -0.70
     doInBackground
    -0.70
    POSITIVE LOGITS
    isLoaded
    0.34
     ped
    0.29
     bas
    0.29
     arca
    0.28
     há
    0.27
     vá
    0.27
     kans
    0.27
     vitality
    0.26
     tela
    0.26
     circulation
    0.26
    Activations Density 0.002%

    No Known Activations