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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 109698
    Prev
    Next
    INDEX
    Explanations

    references to "Voodoo" and related cultural themes

    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
     Voodoo
    -1.00
    Voodoo
    -0.84
     voodoo
    -0.75
    mojo
    -0.53
    Mojo
    -0.48
     Vod
    -0.48
     Mojo
    -0.48
     Eskimo
    -0.42
    oodoo
    -0.42
    ाहरण
    -0.42
    POSITIVE LOGITS
    enumii
    0.50
    migrationBuilder
    0.47
    ChildScrollView
    0.46
    flashdata
    0.43
     BorderRadius
    0.43
    principalColumn
    0.42
    UnsafeEnabled
    0.42
    TestingModule
    0.42
    dyž
    0.41
    visuel
    0.40
    Activations Density 0.004%

    No Known Activations