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. 1-GEMMASCOPE-RES-16K
    6. 9339
    Prev
    Next
    INDEX
    Explanations

    references to 'Central' or contexts associated with central regions or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     waits
    -0.62
     waited
    -0.62
     JSONException
    -0.57
    ộn
    -0.55
     ArrayAdapter
    -0.55
     artists
    -0.52
     saisir
    -0.51
     wait
    -0.51
     impatiently
    -0.51
    izzard
    -0.51
    POSITIVE LOGITS
     Central
    2.07
    Central
    2.00
     CENTRAL
    1.77
    CENTRAL
    1.75
    central
    1.54
     central
    1.41
     sentral
    1.15
    entral
    1.12
     Zentral
    0.98
     zentral
    0.97
    Activations Density 0.155%

    No Known Activations