© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. MLP Out - 131k
    9. 6-GEMMASCOPE-MLP-131K
    11. 110602
    Prev
    Next
    INDEX
    Explanations

    the word "possible."

    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
     possible
    -1.42
    possible
    -1.28
     Possible
    -1.23
    Possible
    -1.19
     POSSIBLE
    -1.18
     posible
    -1.10
     possibles
    -1.02
     possível
    -0.97
     возмо
    -0.97
     possibile
    -0.94
    POSITIVE LOGITS
    expandindo
    0.55
     endwhile
    0.52
     autorytatywna
    0.45
     felicità
    0.45
    jooq
    0.43
    期刊论文
    0.43
    contentLoaded
    0.41
     kasarigan
    0.40
     resourceCulture
    0.40
    EFIAPI
    0.40
    Activations Density 0.009%

    No Known Activations