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. 2260
    Prev
    Next
    INDEX
    Explanations

    numbers and numerical data

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

    "third" or numbers ending with "-rd"

    np_acts-logits-general · gemini-2.0-flash

    third

    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
    asteroido
    -0.54
    !("{}",
    -0.53
     eleventh
    -0.53
     Sixteenth
    -0.53
     eleven
    -0.52
     fifteenth
    -0.51
     sepol
    -0.51
     ¹
    -0.51
     mon
    -0.51
     sixteen
    -0.51
    POSITIVE LOGITS
     third
    1.26
    third
    1.14
     Third
    1.09
    Third
    1.09
     Thirdly
    0.96
     thirds
    0.91
    第三
    0.91
     THIRD
    0.91
     ketiga
    0.90
    3
    0.88
    Activations Density 0.559%

    No Known Activations