© 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. 110176
    Prev
    Next
    INDEX
    Explanations

    names of characters and artists in various contexts

    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
     otomatig
    -0.62
     Roskov
    -0.62
    $_['
    -0.58
    ViewImports
    -0.56
    tagPool
    -0.55
    Демографія
    -0.55
    PerformLayout
    -0.54
     expériment
    -0.52
    styleType
    -0.52
    XmlEnum
    -0.52
    POSITIVE LOGITS
     their
    0.35
     Picchu
    0.34
    Alike
    0.33
     mine
    0.32
     neighboring
    0.32
    CANCE
    0.32
     toothpaste
    0.31
    Erreferentziak
    0.31
     goldfish
    0.31
    bind
    0.30
    Activations Density 0.042%

    No Known Activations