© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. MLP Out - 131k
    9. 6-GEMMASCOPE-MLP-131K
    11. 109320
    Prev
    Next
    INDEX
    Explanations

    specific character sequences or names 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
     유
    -1.92
    유
    -1.58
    的有
    -0.56
     GenerationType
    -0.51
    流
    -0.51
     hữu
    -0.47
    Hentet
    -0.46
    prepareStatement
    -0.46
     للمعارف
    -0.43
    是有
    -0.42
    POSITIVE LOGITS
     poveznice
    0.46
     Autorizaciones
    0.45
    NameInMap
    0.39
    הערות
    0.39
     Contribu
    0.38
    XmlEnum
    0.38
    ="@+
    0.37
    ondissement
    0.37
    blico
    0.36
     contribue
    0.36
    Activations Density 0.001%

    No Known Activations