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. 9879
    Prev
    Next
    INDEX
    Explanations

    instances of the term "Da" and its variations in context, often referring to themes or characters associated with this designation

    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
    IsContent
    -0.90
    |}{\
    -0.89
     propOrder
    -0.88
     itſelf
    -0.87
    Успе
    -0.84
     Fli
    -0.83
    specialchars
    -0.83
    getLog
    -0.82
    httphttps
    -0.82
     Hara
    -0.81
    POSITIVE LOGITS
     Da
    1.95
    Da
    1.91
     da
    1.79
    da
    1.53
     DA
    1.52
    DA
    1.49
     Dahl
    1.09
    Да
    1.03
     да
    1.02
     DAZ
    0.93
    Activations Density 0.038%

    No Known Activations