© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 110039
    Prev
    Next
    INDEX
    Explanations

    references to plans and future intentions

    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
     plans
    -1.70
     Plans
    -1.56
    Plans
    -1.55
     PLANS
    -1.41
    plans
    -1.40
     Pläne
    -1.16
     планы
    -0.91
     planos
    -0.88
     rencana
    -0.79
    计划
    -0.69
    POSITIVE LOGITS
    ̈́
    0.39
     laura
    0.36
    addContainerGap
    0.35
     ApiException
    0.35
     sonore
    0.34
     postIndex
    0.34
    オレ
    0.34
     nakalista
    0.33
     censiti
    0.33
     UIFont
    0.33
    Activations Density 0.004%

    No Known Activations