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. 1650
    Prev
    Next
    INDEX
    Explanations

    terms related to biological processes and their associated metrics

    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
    com
    -0.56
     Pristup
    -0.55
    BeginInit
    -0.54
    require
    -0.53
    kod
    -0.50
    clu
    -0.49
     Photocase
    -0.49
    anh
    -0.49
    Com
    -0.48
    strides
    -0.47
    POSITIVE LOGITS
     للمعارف
    0.78
     ostavi
    0.73
     дописавши
    0.70
    ysacchar
    0.67
    ритори
    0.67
    encodeWith
    0.66
    bonucleic
    0.65
     يتيمه
    0.64
    pidou
    0.64
     مشارکت‌کنندگان
    0.63
    Activations Density 1.274%

    No Known Activations