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. 13149
    Prev
    Next
    INDEX
    Explanations

    concepts related to balance or equilibrium in various contexts

    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
     cão
    -0.73
    .$.
    -0.72
    MLLoader
    -0.71
    angsaan
    -0.69
    mények
    -0.69
    :+:
    -0.69
    rungsseite
    -0.69
    ʊ
    -0.69
     Biggs
    -0.68
     goutte
    -0.65
    POSITIVE LOGITS
     balance
    2.59
     Balance
    2.50
     balances
    2.49
    balance
    2.45
    Balance
    2.38
     BALANCE
    2.27
    BALANCE
    2.20
    balances
    2.14
     balanced
    2.06
     balancing
    2.00
    Activations Density 0.060%

    No Known Activations