© 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. 109966
    Prev
    Next
    INDEX
    Explanations

    the conjunction "and" used to connect sentences or phrases

    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
    IndentedString
    -0.56
    #
    -0.54
    featureID
    -0.51
     Roskov
    -0.44
     maksi
    -0.44
    TargetException
    -0.44
    dataclass
    -0.42
    kaŭ
    -0.42
     mineures
    -0.42
     télécharge
    -0.41
    POSITIVE LOGITS
     nakalista
    0.48
    Билгалдахарш
    0.40
    homonymie
    0.39
    iveau
    0.39
    Cyfeiriadau
    0.39
    SharedDtor
    0.36
    
    0.36
    ślę
    0.35
    NewGuid
    0.35
    esterno
    0.35
    Activations Density 0.020%

    No Known Activations