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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 110292
    Prev
    Next
    INDEX
    Explanations

    variations of the word "idyl" and related terms

    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
    idy
    -1.10
    idyl
    -0.66
     ModelExpression
    -0.60
     kasarigan
    -0.53
    tidy
    -0.46
     للاسماء
    -0.45
    ngrx
    -0.44
    idic
    -0.42
    CppMethod
    -0.41
     useEffect
    -0.41
    POSITIVE LOGITS
    tvguidetime
    0.49
    Erreferentziak
    0.47
    Lähteet
    0.46
    DockStyle
    0.44
     angekommen
    0.42
    zkiem
    0.40
     
    0.40
    Географиясе
    0.38
    arbre
    0.38
     спе
    0.37
    Activations Density 0.005%

    No Known Activations