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. 12997
    Prev
    Next
    INDEX
    Explanations

    terms related to disputes or conflicts, particularly in legal or formal 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
     Go
    -0.52
     panggilan
    -0.52
    ,:),
    -0.51
    ﷺ
    -0.50
     mengal
    -0.49
     excellent
    -0.49
    につなが
    -0.48
     tölt
    -0.48
     menak
    -0.47
     Hines
    -0.47
    POSITIVE LOGITS
     dispute
    1.71
     disputes
    1.69
     controversy
    1.53
     disputed
    1.47
     debate
    1.46
     controversies
    1.37
     debates
    1.36
     Dispute
    1.36
     Disputes
    1.35
     Controversy
    1.34
    Activations Density 0.275%

    No Known Activations