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. 109627
    Prev
    Next
    INDEX
    Explanations

    references to software packages and installation commands

    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
    ardless
    -0.42
     viewType
    -0.41
     systemctl
    -0.38
     eleições
    -0.34
     Politique
    -0.32
    systemctl
    -0.32
    migrationBuilder
    -0.32
     esterni
    -0.31
    Fordítás
    -0.31
    Poids
    -0.31
    POSITIVE LOGITS
     arşivlendi
    0.51
     uLocal
    0.46
     Exacts
    0.45
    flage
    0.45
    umpang
    0.45
     propOrder
    0.45
     createState
    0.45
    XmlAccessType
    0.45
    writeFieldEnd
    0.45
    quested
    0.43
    Activations Density 0.023%

    No Known Activations