© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. MLP Out - 131k
    9. 6-GEMMASCOPE-MLP-131K
    11. 109105
    Prev
    Next
    INDEX
    Explanations

    references to drains and draining processes

    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
     drain
    -2.20
     Drain
    -1.95
    Drain
    -1.77
     drains
    -1.72
    drain
    -1.69
     DRAIN
    -1.48
     draining
    -1.30
     drainage
    -1.27
     drained
    -1.24
     Drainage
    -1.17
    POSITIVE LOGITS
    SequentialGroup
    0.52
    المشاركات
    0.51
    期刊论文
    0.51
    
    0.51
    PropertyChanging
    0.47
     tartalomajánló
    0.46
     كومونز
    0.46
    Microkernel
    0.45
    ThroughAttribute
    0.44
    SharedCtor
    0.44
    Activations Density 0.001%

    No Known Activations