© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 13-GEMMASCOPE-RES-65K
    11. 56493
    Prev
    Next
    INDEX
    Explanations

    undesired or negative punctuation markers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     تضيفلها
    -0.88
    PreferredItem
    -0.85
     defaultstate
    -0.84
    AccessorTable
    -0.80
    iNdEx
    -0.80
     rodríguez
    -0.77
     Monfieur
    -0.75
     Houſe
    -0.75
     pleaſure
    -0.74
     iNdEx
    -0.73
    POSITIVE LOGITS
     فريبيس
    0.75
     Col
    0.47
    ,
    0.46
     senti
    0.44
     En
    0.43
    libft
    0.43
    ),
    0.42
    ksjon
    0.42
     col
    0.41
     def
    0.40
    Activations Density 0.000%

    No Known Activations