© 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. 110098
    Prev
    Next
    INDEX
    Explanations

    terms related to monitoring or surveillance functions

    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
     setOpen
    -0.36
     فض
    -0.35
    SequentialGroup
    -0.35
     spill
    -0.33
     PyTuple
    -0.33
    CompilerServices
    -0.33
    BASELINE
    -0.33
     galle
    -0.32
     discre
    -0.32
    InteropServices
    -0.32
    POSITIVE LOGITS
     automatiques
    0.59
     Autorisations
    0.54
     automáticamente
    0.52
     оригіналу
    0.52
     Autorizaciones
    0.52
     ritratto
    0.51
     amitié
    0.50
     juridiques
    0.50
     pitié
    0.50
     wiedzy
    0.50
    Activations Density 0.092%

    No Known Activations