© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. MLP Out - 131k
    5. 6-GEMMASCOPE-MLP-131K
    6. 110058
    Prev
    Next
    INDEX
    Explanations

    phrases related to time and sequences of events

    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
    GEBURTS
    -0.49
     initComponents
    -0.45
     ProtoMessage
    -0.44
    __*/
    -0.43
    cortina
    -0.42
     Meksiku
    -0.40
    NameInMap
    -0.40
    angliski
    -0.40
     دیکھیے
    -0.39
     استنادى
    -0.39
    POSITIVE LOGITS
    RefNanny
    0.47
     next
    0.40
     immediately
    0.38
     prossimo
    0.37
    翌
    0.37
     następ
    0.37
     future
    0.36
     immediate
    0.36
     Wesen
    0.36
    ünf
    0.36
    Activations Density 0.108%

    No Known Activations