© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. MLP Out - 131k
    9. 6-GEMMASCOPE-MLP-131K
    11. 109053
    Prev
    Next
    INDEX
    Explanations

    instances of fear or being scared

    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
     scared
    -1.55
     frightened
    -1.19
    scared
    -1.15
     scares
    -1.04
     scare
    -1.00
     terrified
    -0.94
    Scared
    -0.93
     frighten
    -0.89
     scaring
    -0.89
     asust
    -0.79
    POSITIVE LOGITS
     Савезне
    0.70
    expandindo
    0.62
    XmlAccessType
    0.61
    GOTREF
    0.59
    tagHelperRunner
    0.59
    ỡng
    0.59
    OGND
    0.57
     propOrder
    0.57
    CppMethod
    0.57
     незавершена
    0.56
    Activations Density 0.001%

    No Known Activations