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. 2822
    Prev
    Next
    INDEX
    Explanations

    technical terms and metrics related to medical and scientific studies

    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
    ACKS
    -0.61
     autorytatywna
    -0.58
    ագրություններ
    -0.57
    WARNINGS
    -0.56
    таратура
    -0.56
    rawdź
    -0.55
    mitian
    -0.54
     willed
    -0.54
     intermédiaire
    -0.54
     whoſe
    -0.54
    POSITIVE LOGITS
     rate
    1.03
     ratio
    0.84
     intensity
    0.83
     value
    0.82
     size
    0.80
     index
    0.79
     count
    0.79
     volume
    0.78
     score
    0.78
     capacity
    0.76
    Activations Density 1.798%

    No Known Activations