© 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-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 5591
    Prev
    Next
    INDEX
    Explanations

    phrases related to recommendations and suggestions in various contexts

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

    Recommendation or suggestion

    np_acts-logits-general · gemini-2.0-flash

    recommendation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    strptime
    -0.55
     ostavi
    -0.54
    ImageContext
    -0.52
    انيف
    -0.50
    Liar
    -0.49
     mergeFrom
    -0.47
    unkel
    -0.47
    centerY
    -0.44
    Personendaten
    -0.44
    :✨
    -0.44
    POSITIVE LOGITS
     recommendation
    3.48
     recommendations
    3.47
     recommended
    3.18
     recommend
    3.15
     recommending
    2.98
     Recommendations
    2.94
     recommends
    2.92
     Recommendation
    2.91
    recommendation
    2.78
    Recommendations
    2.76
    Activations Density 0.544%

    No Known Activations