Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 109502
    Prev
    Next
    INDEX
    Explanations

    references to significant historical events or changes impacting society

    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
     diarias
    -0.30
    transQ
    -0.29
     EClass
    -0.29
    enumii
    -0.28
     alugar
    -0.25
     ложки
    -0.24
     consectetur
    -0.23
     itinéraires
    -0.23
    lösen
    -0.23
     dientes
    -0.23
    POSITIVE LOGITS
    selig
    0.61
     informée
    0.61
     Administrativna
    0.60
    arangay
    0.57
     AssemblyCulture
    0.57
    bronn
    0.57
     imagui
    0.56
     Gau
    0.56
    GEBURTSDATUM
    0.55
    ﭔ
    0.55
    Activations Density 0.022%

    No Known Activations