© 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. 108751
    Prev
    Next
    INDEX
    Explanations

    verbs and nouns related to official statements or announcements

    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
     jsme
    -0.38
     hende
    -0.36
     практика
    -0.35
     announcing
    -0.35
    формация
    -0.32
     intercamb
    -0.31
     beina
    -0.31
     geçti
    -0.31
     sting
    -0.31
     announce
    -0.31
    POSITIVE LOGITS
     للاسماء
    0.76
     ModelExpression
    0.63
     يتيمه
    0.54
     utafitiHapana
    0.54
    AsUp
    0.54
     témoig
    0.51
    OGND
    0.49
    apatalk
    0.48
    tvguidetime
    0.48
    localctx
    0.47
    Activations Density 0.008%

    No Known Activations