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. 3-GEMMASCOPE-RES-16K
    6. 10883
    Prev
    Next
    INDEX
    Explanations

    actions related to financial transactions and activities involving payments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ,
    -0.52
     跳转至
    -0.46
    ...
    -0.45
     </
    -0.44
    </
    -0.41
     {};
    -0.41
     وتسجيلات
    -0.40
    .</
    -0.40
     ओर
    -0.38
     
    -0.37
    POSITIVE LOGITS
     itſelf
    0.92
     Houſe
    0.90
    NUMX
    0.88
     myſelf
    0.87
     Paglinawan
    0.86
     Chriftian
    0.82
    TagMode
    0.81
     IBRARY
    0.79
     Theſe
    0.78
     $_"
    0.77
    Activations Density 0.833%

    No Known Activations