Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 12-GEMMASCOPE-RES-16K
    6. 2082
    Prev
    Next
    INDEX
    Explanations

    phrases regarding conditions, agreements, and exceptions in legal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AccessorTable
    -0.84
    Kaynakça
    -0.64
    ontale
    -0.62
     createSlice
    -0.62
    ArgsConstructor
    -0.59
     سكانية
    -0.57
    InputBorder
    -0.57
    ={`${
    -0.56
    DispatchToProps
    -0.56
    IntoConstraints
    -0.55
    POSITIVE LOGITS
     otherwise
    0.72
    Otherwise
    0.63
     OTHERWISE
    0.63
     Otherwise
    0.57
    cyklopedia
    0.55
    otherwise
    0.53
    IContainer
    0.53
     already
    0.52
    TestTools
    0.50
     necessarily
    0.50
    Activations Density 0.445%

    No Known Activations