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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 13960
    Prev
    Next
    INDEX
    Explanations

    legal terminology and principles related to court rulings and case law

    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
    szön
    -0.58
    msgSender
    -0.53
    setopt
    -0.52
     dores
    -0.51
    り返
    -0.50
    Composable
    -0.50
     affichés
    -0.50
     colectiva
    -0.49
    ReusableCell
    -0.49
    Rhestr
    -0.48
    POSITIVE LOGITS
     Roskov
    0.64
    Judicial
    0.56
     Normdatei
    0.54
    asyarakat
    0.54
     snippetHide
    0.54
     NUKAT
    0.54
    IVEREF
    0.52
     `"
    0.51
    >");
    
    0.51
    brata
    0.50
    Activations Density 2.077%

    No Known Activations