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. 5-GEMMASCOPE-RES-16K
    6. 14164
    Prev
    Next
    INDEX
    Explanations

    names and references related to legal proceedings or legal entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ViewImports
    -0.99
    enumi
    -0.91
     Interchange
    -0.85
     Archaeology
    -0.85
    Rüyada
    -0.85
    ftagPool
    -0.85
     مشين
    -0.82
    ształ
    -0.81
    RegressionTest
    -0.80
    HasBeenSet
    -0.80
    POSITIVE LOGITS
     US
    1.20
     USA
    0.86
     Federal
    0.85
     United
    0.84
    US
    0.81
     States
    0.77
     federal
    0.76
     American
    0.72
     U
    0.68
     World
    0.63
    Activations Density 0.126%

    No Known Activations