Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 109473
    Prev
    Next
    INDEX
    Explanations

    elements related to physical or emotional well-being and health

    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
     brain
    -0.96
     brains
    -0.89
    brain
    -0.84
     mind
    -0.80
     Brain
    -0.79
     minds
    -0.78
     BRAIN
    -0.77
     MIND
    -0.74
    Brain
    -0.72
     cerveau
    -0.71
    POSITIVE LOGITS
    addContainerGap
    0.45
     thiệu
    0.42
     untranslated
    0.41
     calendriers
    0.41
     undef
    0.40
    RenderAtEndOf
    0.40
     հղումներ
    0.39
     Complaint
    0.38
     unsupervised
    0.38
    Discre
    0.38
    Activations Density 0.040%

    No Known Activations