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. 673
    Prev
    Next
    INDEX
    Explanations

    references to legal proceedings and concepts related to justice

    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
     There
    -0.69
     It
    -0.64
     it
    -0.62
     there
    -0.60
    There
    -0.58
     ihr
    -0.53
    It
    -0.53
     them
    -0.52
     You
    -0.49
    there
    -0.47
    POSITIVE LOGITS
    setVerticalGroup
    1.09
    principalTable
    0.99
     <<<<<<<<<<<<<<
    0.95
    protoimpl
    0.95
     resourceCulture
    0.93
    rungsseite
    0.92
     تضيفلها
    0.92
     bezeichneter
    0.89
    المناصب
    0.88
     OFDb
    0.86
    Activations Density 0.391%

    No Known Activations