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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 9282
    Prev
    Next
    INDEX
    Explanations

    terms related to reproduction and health issues in livestock, particularly focusing on cattle and sheep

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    mybatisplus
    -0.88
     الحره
    -0.87
    TagMode
    -0.81
      (
    -0.73
    avits
    -0.73
    })$}
    -0.73
     Италијани
    -0.71
    Билгалдахарш
    -0.69
    FTFY
    -0.69
    ---*/
    -0.69
    POSITIVE LOGITS
    <strong>
    0.51
    ta
    0.50
    $\
    0.50
    //
    0.49
    <b>
    0.47
    ð
    0.47
     oftentimes
    0.46
    ีย
    0.46
    $
    0.46
    L
    0.45
    Activations Density 0.097%

    No Known Activations