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. 2617
    Prev
    Next
    INDEX
    Explanations

    specific zoning and legal terminology related to properties and ordinances

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

    Describes the direction or orientation of something

    np_acts-logits-general · gemini-2.0-flash

    runs along or between things

    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
     Normdatei
    -0.62
    MLLoader
    -0.55
     nahilalakip
    -0.55
     للمعارف
    -0.53
    poort
    -0.51
     hats
    -0.51
     terecht
    -0.51
     papilla
    -0.51
    interopRequire
    -0.51
    volmente
    -0.50
    POSITIVE LOGITS
     lengthwise
    1.08
     length
    1.05
     liné
    1.02
     sepanjang
    1.01
     вдоль
    1.00
     along
    0.94
     rows
    0.94
     row
    0.93
     entlang
    0.92
     width
    0.90
    Activations Density 0.464%

    No Known Activations