© 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. 109892
    Prev
    Next
    INDEX
    Explanations

    phrases indicating possibility or uncertainty

    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
     may
    -0.38
    abstractmethod
    -0.33
     intptr
    -0.32
     Voss
    -0.32
     electro
    -0.31
     Hagen
    -0.31
    rungsseite
    -0.30
     custos
    -0.30
    may
    -0.29
     Keim
    -0.29
    POSITIVE LOGITS
    ſelves
    0.60
    resaid
    0.58
    <unused43>
    0.57
    Personensuche
    0.57
    <unused41>
    0.57
    <unused28>
    0.57
    <unused74>
    0.57
    <unused79>
    0.57
    <unused42>
    0.57
    <unused17>
    0.57
    Activations Density 0.003%

    No Known Activations