© 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. 108651
    Prev
    Next
    INDEX
    Explanations

    references to Mars

    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
     Mars
    -2.23
    Mars
    -2.03
     mars
    -1.63
     MARS
    -1.49
    mars
    -1.43
    火星
    -0.98
     Martian
    -0.96
     Marsha
    -0.93
     Marsden
    -0.79
     marshes
    -0.79
    POSITIVE LOGITS
     GenerationType
    0.47
    InjectMocks
    0.47
    ttemberg
    0.45
    MockBean
    0.44
     Zauber
    0.44
    KURZBESCHREIBUNG
    0.44
    prepareStatement
    0.43
     виправивши
    0.41
    Herzliche
    0.40
    GEBURTSDATUM
    0.40
    Activations Density 0.001%

    No Known Activations