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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 11-GEMMASCOPE-RES-16K
    6. 5053
    Prev
    Next
    INDEX
    Explanations

    mentions of legal procedures related to grievances and court decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DebuggerNonUser
    -0.55
     MainAxisSize
    -0.50
     StatefulWidget
    -0.48
    BagConstraints
    -0.47
    ophanes
    -0.47
    AxisAlignment
    -0.47
    setupUi
    -0.47
    keyColumn
    -0.46
    ungkinan
    -0.46
     savons
    -0.45
    POSITIVE LOGITS
    ksikon
    0.67
    hyrchwyd
    0.61
    Geplaatst
    0.54
    riction
    0.54
    uarga
    0.53
    ➟
    0.53
     Rank
    0.53
    webElementXpaths
    0.52
     Nivel
    0.52
    mybatisplus
    0.52
    Activations Density 1.005%

    No Known Activations