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. 5-GEMMASCOPE-RES-16K
    6. 16192
    Prev
    Next
    INDEX
    Explanations

    references to medical treatments and patient conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Paglinawan
    -0.51
    OGND
    -0.49
    ArgumentParser
    -0.48
    RegressionTest
    -0.47
    mybatisplus
    -0.44
     defaultstate
    -0.44
    <bos>
    -0.43
    fra
    -0.42
     Mete
    -0.42
    vyn
    -0.42
    POSITIVE LOGITS
    niająca
    0.72
    下载附件
    0.70
     onCancelled
    0.66
     صوتيه
    0.66
    lossians
    0.65
    nemia
    0.63
    onnaissance
    0.62
    ttää
    0.60
    netje
    0.60
    ouflage
    0.60
    Activations Density 0.459%

    No Known Activations