© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. MLP Out - 16k
    9. 19-GEMMASCOPE-MLP-16K
    11. 8275
    Prev
    Next
    INDEX
    Explanations

    phrases related to warranties or guarantees for products, particularly in the context of recreational or light-duty applications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-mlp-16k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_19/width_16k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_mlp_out
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -0.71
    opsida
    -0.57
     damage
    -0.54
    ernalia
    -0.54
     arşivlendi
    -0.53
     оригіналу
    -0.53
    damage
    -0.51
     humaines
    -0.51
     Beatrix
    -0.51
     Metacritic
    -0.50
    POSITIVE LOGITS
     commercial
    1.42
    Commercial
    1.34
     Commercial
    1.31
    commercial
    1.24
     COMMERCIAL
    1.15
     commer
    1.06
     comercial
    1.05
    COMMERCIAL
    1.02
     COMERC
    0.99
     komer
    0.98
    Activations Density 0.301%

    No Known Activations