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. 12574
    Prev
    Next
    INDEX
    Explanations

    terms related to legal custody and bail situations

    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
    yaszt
    -0.56
    idom
    -0.52
    Personendaten
    -0.51
     प्रदेश
    -0.50
    OfYear
    -0.49
     famí
    -0.49
     convictions
    -0.49
    stry
    -0.48
    ítulo
    -0.48
    ペン
    -0.48
    POSITIVE LOGITS
     bail
    1.21
     bond
    1.14
    Bail
    1.03
     Bail
    0.99
    bail
    0.94
     Bond
    0.84
    bond
    0.83
     bai
    0.83
    Bond
    0.81
     bonds
    0.77
    Activations Density 0.363%

    No Known Activations