© 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. 109082
    Prev
    Next
    INDEX
    Explanations

    occurrences of specific suffix patterns in the text

    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
    isse
    -1.67
    ISSE
    -1.34
    asse
    -1.18
    issen
    -0.90
    issé
    -0.84
    ssen
    -0.84
    isses
    -0.81
    essen
    -0.81
    ßen
    -0.81
    ASSE
    -0.80
    POSITIVE LOGITS
    astify
    0.54
    tagHelperRunner
    0.53
    Gambas
    0.49
    ConstraintMaker
    0.47
    EndGlobalSection
    0.46
     صوتيه
    0.46
    Referències
    0.46
    WaitGroup
    0.45
    writeField
    0.44
    ValueStyle
    0.43
    Activations Density 0.007%

    No Known Activations