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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 108432
    Prev
    Next
    INDEX
    Explanations

    mentions of stainless steel

    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
     steel
    -0.68
     Steel
    -0.59
     STEEL
    -0.56
    steel
    -0.56
    Steel
    -0.53
     المعيارى
    -0.51
     stainless
    -0.45
     stål
    -0.40
    teel
    -0.39
     Stainless
    -0.39
    POSITIVE LOGITS
    setVerticalGroup
    0.74
    ChildScrollView
    0.52
    abestanden
    0.51
    SharedDtor
    0.49
     ब्रेकडाउन
    0.48
    tagHelperRunner
    0.47
     tartalomajánló
    0.46
    Jereo
    0.46
     saites
    0.46
     ویکی‌پدی
    0.46
    Activations Density 0.002%

    No Known Activations