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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 28072
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly periods

    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
     âm
    -0.32
    verifyException
    -0.31
    dialement
    -0.31
     haine
    -0.29
     Roskov
    -0.29
    ButtonItem
    -0.28
     HasFactory
    -0.28
    ハマ
    -0.28
     presa
    -0.28
     hypnosis
    -0.28
    POSITIVE LOGITS
     ब्रेकडाउन
    0.67
     defaultstate
    0.64
    Personendaten
    0.58
    oneofs
    0.58
     للمعارف
    0.57
    webElementXpaths
    0.56
    expandindo
    0.54
    انيف
    0.53
     సౌకర్య
    0.52
    ViewFeatures
    0.52
    Activations Density 0.008%

    No Known Activations