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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 21883
    Prev
    Next
    INDEX
    Explanations

    phrases related to international cooperation and dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     Normdatei
    -0.47
    Autoritní
    -0.44
     חיצוניים
    -0.42
    Lähteet
    -0.41
     denn
    -0.40
     hast
    -0.38
     referenties
    -0.36
     utah
    -0.36
     réparer
    -0.36
     blad
    -0.35
    POSITIVE LOGITS
     mutual
    0.67
     bilateral
    0.63
    mutual
    0.59
     reciprocal
    0.57
     mutually
    0.57
    Mutual
    0.56
     çerçe
    0.54
     Bilateral
    0.52
     recipro
    0.50
    setVerticalGroup
    0.49
    Activations Density 0.031%

    No Known Activations