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. 35367
    Prev
    Next
    INDEX
    Explanations

    emoticons or symbols representing feelings and reactions

    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
     الحره
    -0.56
    oredCriteria
    -0.54
    CloseOperation
    -0.47
    scn
    -0.46
    ]-->
    -0.46
     Exacts
    -0.45
     Ran
    -0.44
     Dh
    -0.42
     Rask
    -0.42
     Jh
    -0.41
    POSITIVE LOGITS
    
    0.93
    
    0.61
     gouvernements
    0.56
    RegressionTest
    0.55
     Majefty
    0.52
     costuras
    0.52
     pouvoirs
    0.48
     hígado
    0.48
     déliv
    0.47
    
    0.47
    Activations Density 0.000%

    No Known Activations