© 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. 13232
    Prev
    Next
    INDEX
    Explanations

    phrases related to overcoming challenges and managing tasks

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

    Following "to" and the word "find"

    np_acts-logits-general · gemini-2.0-flash

    managed to find/get/obtain

    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
     setTotal
    -0.61
     gärna
    -0.60
    sprechend
    -0.59
     étudi
    -0.59
     vouloir
    -0.57
    Jereo
    -0.57
     rechercher
    -0.57
    出版年
    -0.56
    NewUrlParser
    -0.54
    potential
    -0.54
    POSITIVE LOGITS
     convince
    1.04
     persuade
    1.01
     find
    0.92
     persuading
    0.91
     persuaded
    0.89
     convincing
    0.89
     successfully
    0.88
     obtain
    0.87
     convinced
    0.79
     convinces
    0.79
    Activations Density 0.413%

    No Known Activations