© 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. 16-GEMMASCOPE-RES-16K
    11. 8515
    Prev
    Next
    INDEX
    Explanations

    phrases that convey benefits and features of services or products

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

    Followed by prepositions or conjunctions

    np_acts-logits-general · gemini-2.0-flash

    guarantee

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    THISDAY
    -0.51
     okuyayım
    -0.50
     Leider
    -0.47
     analogy
    -0.46
    erweise
    -0.46
     innocently
    -0.46
    orElse
    -0.45
    WriteTagHelper
    -0.45
    ironically
    -0.45
    __":
    -0.44
    POSITIVE LOGITS
     guaranteed
    0.94
     guarantee
    0.90
     garanti
    0.90
     guarantees
    0.85
     garan
    0.82
     Guarantee
    0.82
     гаранти
    0.80
     Guarante
    0.79
    Guarantee
    0.79
     garantie
    0.78
    Activations Density 0.089%

    No Known Activations