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. 20-GEMMASCOPE-RES-16K
    6. 12245
    Prev
    Next
    INDEX
    Explanations

    concepts related to balance and fairness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "balance."

    np_acts-logits-general · gemini-2.0-flash

    balance between and

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     وتسجيلات
    -0.83
    lapsingToolbar
    -0.81
    ThroughAttribute
    -0.66
    TagMode
    -0.64
    ollectionView
    -0.63
     gynhyrchwyd
    -0.62
    conazole
    -0.62
    mények
    -0.62
    PhysRevD
    -0.62
    AddTagHelper
    -0.59
    POSITIVE LOGITS
     balances
    1.26
    balances
    1.17
     Balance
    1.16
    balance
    1.13
     balance
    1.13
    Balance
    1.09
     BALANCE
    1.08
    BALANCE
    1.07
     balan
    1.04
    Balances
    1.03
    Activations Density 0.072%

    No Known Activations