© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. MLP Out - 131k
    5. 6-GEMMASCOPE-MLP-131K
    6. 109058
    Prev
    Next
    INDEX
    Explanations

    negations or phrases indicating the absence of something

    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
     betweenstory
    -0.49
    
    -0.48
    Obrázky
    -0.47
     Normdatei
    -0.46
    ExtendWith
    -0.45
    KEYCODE
    -0.45
    存于互联网档案馆
    -0.45
    OnAdd
    -0.43
    Autoritní
    -0.43
     senare
    -0.42
    POSITIVE LOGITS
     disponibilités
    0.56
     himo
    0.39
     malang
    0.36
     badges
    0.36
     bande
    0.35
     znak
    0.35
     Bartholo
    0.35
    bootstrapcdn
    0.35
     fark
    0.34
     visitor
    0.34
    Activations Density 0.009%

    No Known Activations