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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 109264
    Prev
    Next
    INDEX
    Explanations

    references to pumpkins and pumpkin-related items or themes

    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
     pumpkin
    -1.65
     Pumpkin
    -1.48
     pumpkins
    -1.38
    Pumpkin
    -1.35
    pumpkin
    -1.35
    南瓜
    -0.78
     PUM
    -0.75
    🎃
    -0.66
    pump
    -0.64
    Pump
    -0.63
    POSITIVE LOGITS
    /*++
    0.45
    KURZBESCHREIBUNG
    0.40
    ViewImports
    0.39
     مرئيه
    0.39
    Décès
    0.38
     DPRD
    0.38
     rapat
    0.37
    @[+][
    0.37
    astify
    0.37
     sufferer
    0.36
    Activations Density 0.001%

    No Known Activations