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. 109781
    Prev
    Next
    INDEX
    Explanations

    references to identifiers and numeric data in technical 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
    HandlerContext
    -0.47
    :✨
    -0.45
    ">#
    -0.38
     CONTEXT
    -0.35
    蓄
    -0.34
    layoutControl
    -0.34
    findpost
    -0.34
    LayoutInflater
    -0.34
    sing
    -0.34
    ɵɵelementStart
    -0.34
    POSITIVE LOGITS
    әрмәләр
    0.50
     pinulongan
    0.49
    WithIOException
    0.48
    лтамалар
    0.47
     étoient
    0.47
     ब्रेकडाउन
    0.45
     Ressources
    0.45
     méri
    0.45
     préfé
    0.45
     nakalista
    0.44
    Activations Density 0.161%

    No Known Activations