© 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. 109206
    Prev
    Next
    INDEX
    Explanations

    terms related to gadgets and their functionalities

    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
     gadget
    -1.54
     gadgets
    -1.45
     Gadget
    -1.26
     Gadgets
    -1.25
    gadget
    -1.15
    Gadget
    -1.07
    Gad
    -0.74
    gad
    -0.74
    GAD
    -0.67
     giz
    -0.64
    POSITIVE LOGITS
     uș
    0.45
    AndEndTag
    0.44
    دانشنامهٔ
    0.43
    ENODE
    0.43
    zków
    0.42
    Décès
    0.41
    endcsname
    0.41
     exportación
    0.41
    abestanden
    0.40
    èdent
    0.40
    Activations Density 0.001%

    No Known Activations