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. 109619
    Prev
    Next
    INDEX
    Explanations

    HTML attributes

    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
     ujednoznacz
    -1.05
    SharedCtor
    -0.95
     ModelExpression
    -0.92
    verwijspagina
    -0.86
     increí
    -0.85
    <unused43>
    -0.85
    <unused3>
    -0.85
    RenderAtEndOf
    -0.85
    <unused41>
    -0.85
    [@BOS@]
    -0.84
    POSITIVE LOGITS
    ↵↵
    0.49
    ↵
    0.48
    '
    0.42
     
    0.34
    <eos>
    0.33
    ado
    0.33
      
    0.31
    <bos>
    0.31
    ps
    0.31
     Mal
    0.30
    Activations Density 0.006%

    No Known Activations