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. 109537
    Prev
    Next
    INDEX
    Explanations

    numerical values or identification references, particularly in lists or structured data

    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
     copy
    -0.33
     tls
    -0.31
     pills
    -0.30
     Gies
    -0.30
     choice
    -0.30
    inst
    -0.30
     Event
    -0.29
     adds
    -0.29
    gameserver
    -0.29
    copy
    -0.29
    POSITIVE LOGITS
     propOrder
    0.88
     Administrativna
    0.77
     ExecuteAsync
    0.75
    GTCX
    0.74
    LookAnd
    0.74
    complexContent
    0.74
     snippetHide
    0.72
    oa̍t
    0.71
    تقاوى
    0.71
     resourceCulture
    0.70
    Activations Density 0.034%

    No Known Activations