Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 19-GEMMASCOPE-RES-16K
    6. 298
    Prev
    Next
    INDEX
    Explanations

    terms related to medical examinations and diagnostics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Chham
    -0.51
    findpost
    -0.47
    ValueGenerated
    -0.46
     CreateTagHelper
    -0.45
     насељу
    -0.45
    Restaurante
    -0.45
    AllowUser
    -0.45
    GOTREF
    -0.44
     enroll
    -0.44
     sunsets
    -0.44
    POSITIVE LOGITS
     inspection
    1.89
     examination
    1.78
     inspect
    1.66
     inspecting
    1.66
     inspected
    1.61
     Inspection
    1.59
     inspections
    1.58
     Examination
    1.54
     inspec
    1.52
    Inspection
    1.49
    Activations Density 0.404%

    No Known Activations