© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 2233
    Prev
    Next
    INDEX
    Explanations

    elements related to pop culture and celebrity news

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Infórmanos
    -0.51
     publiques
    -0.46
    spesies
    -0.43
     Penelitian
    -0.43
     dítě
    -0.43
     culturel
    -0.42
     fondation
    -0.42
     distinto
    -0.42
     виправивши
    -0.41
     duquel
    -0.41
    POSITIVE LOGITS
     goodies
    0.84
     nifty
    0.79
     whopping
    0.72
     critters
    0.72
     outta
    0.69
     dodgy
    0.69
     newbies
    0.68
     gals
    0.68
     hefty
    0.68
     Aussie
    0.67
    Activations Density 2.379%

    No Known Activations