© 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. 110963
    Prev
    Next
    INDEX
    Explanations

    references to pellets in various contexts, indicating a focus on pellet-related processes or products

    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
     pellets
    -1.88
     pellet
    -1.80
    pelle
    -1.43
     Pelle
    -1.34
     pelle
    -1.22
    pel
    -0.96
     Pel
    -0.94
     pel
    -0.94
    Pel
    -0.92
     Pell
    -0.90
    POSITIVE LOGITS
     Autorizaciones
    0.57
     Autorisations
    0.41
     estrictamente
    0.41
     szolg
    0.38
     nakalista
    0.37
    AddTagHelper
    0.36
    インター
    0.36
    botas
    0.35
    WriteBarrier
    0.35
    そこに
    0.34
    Activations Density 0.002%

    No Known Activations