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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 109774
    Prev
    Next
    INDEX
    Explanations

    the concept of uniqueness 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
     uniquely
    -1.23
     peculiarly
    -0.69
    quely
    -0.60
    ValueStyle
    -0.52
     distin
    -0.52
     unusually
    -0.48
    Specifically
    -0.48
     specifically
    -0.47
    IContainer
    -0.47
     CanadaChoose
    -0.46
    POSITIVE LOGITS
     MonoBehaviour
    0.48
    KommentareTeilen
    0.47
     deseos
    0.42
     Geschmack
    0.42
     outono
    0.41
    Aholisi
    0.41
     pratos
    0.40
     perfección
    0.38
     provecho
    0.36
    basicConfig
    0.36
    Activations Density 0.001%

    No Known Activations