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. 14611
    Prev
    Next
    INDEX
    Explanations

    references to legal terms and defendants

    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
     Italijanski
    -0.61
    IUrlHelper
    -0.60
     дописавши
    -0.57
     Савезне
    -0.57
    зулта
    -0.55
    abetes
    -0.53
     ostavi
    -0.53
    rrggbb
    -0.50
    LOYEES
    -0.50
    <bos>
    -0.48
    POSITIVE LOGITS
    ScopeManager
    0.69
     ComVisible
    0.61
     ProtoMessage
    0.58
    HomeAsUp
    0.58
     TextInputType
    0.58
    >--}}
    0.57
     Turi
    0.55
     fieldNum
    0.55
    LEncoder
    0.54
    ordning
    0.54
    Activations Density 0.733%

    No Known Activations