© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 15365
    Prev
    Next
    INDEX
    Explanations

    references to data access and usage in marketing contexts

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

    providing or sending something

    np_acts-logits-general · gemini-2.0-flash

    sending and delivery

    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
     CreateTagHelper
    -0.84
     beginnetje
    -0.61
    complexContent
    -0.61
    原始内容存档于
    -0.59
    RegressionTest
    -0.58
    MemoryWarning
    -0.57
     awakeFromNib
    -0.56
     velkommen
    -0.51
    olidation
    -0.49
    bation
    -0.49
    POSITIVE LOGITS
     supplying
    1.61
     deliver
    1.49
     delivering
    1.45
     delivery
    1.39
     supply
    1.38
     delivered
    1.36
     provide
    1.36
     supplied
    1.34
     providing
    1.33
     delivers
    1.32
    Activations Density 0.559%

    No Known Activations