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. 10683
    Prev
    Next
    INDEX
    Explanations

    references to music education and training

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

    Followed by names of educational institutions

    np_acts-logits-general · gemini-2.0-flash

    college and university names

    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
    GetAxis
    -0.48
     locker
    -0.46
     drin
    -0.43
     BrowserModule
    -0.42
    الإنجليزية
    -0.42
     lockers
    -0.42
     Obrador
    -0.42
     coefficients
    -0.42
     retr
    -0.42
    +#+#
    -0.42
    POSITIVE LOGITS
     college
    0.93
     colleges
    0.92
     schools
    0.91
     school
    0.85
     institution
    0.82
     College
    0.81
    college
    0.79
     institutions
    0.79
     Colleges
    0.78
     secondary
    0.77
    Activations Density 0.239%

    No Known Activations