Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 10139
    Prev
    Next
    INDEX
    Explanations

    frequency of the pronoun 'you' in various contexts

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

    Statements or opinions using "I", "you", or "we"

    np_acts-logits-general · gemini-2.0-flash

    subject pronoun followed by state or action

    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
     geweest
    -0.95
     récente
    -0.84
    recently
    -0.81
    Were
    -0.80
     recently
    -0.79
     đã
    -0.79
     Recently
    -0.76
    Recently
    -0.74
     weren
    -0.73
     occurred
    -0.72
    POSITIVE LOGITS
     make
    0.98
     take
    0.96
     get
    0.94
     decide
    0.86
     become
    0.85
     develop
    0.83
     give
    0.81
     create
    0.81
     bring
    0.79
     add
    0.78
    Activations Density 0.292%

    No Known Activations