© 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-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 20752
    Prev
    Next
    INDEX
    Explanations

    promotional phrases encouraging action or engagement with a service or product

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Circuit court cases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ThroughAttribute
    -0.80
     ***!
    -0.64
     resourceCulture
    -0.58
    RegressionTest
    -0.56
    TypedDataSet
    -0.55
    Personendaten
    -0.54
    ьаж
    -0.54
    msgTypes
    -0.53
     arşivlendi
    -0.53
    .*")]
    -0.52
    POSITIVE LOGITS
     shopping
    0.46
     purchases
    0.39
    shopping
    0.34
     Shopping
    0.34
     purchase
    0.33
     Dress
    0.31
     dress
    0.31
     Purchases
    0.31
     cheap
    0.31
    委員
    0.31
    Activations Density 0.003%

    No Known Activations