© 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-2-2B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 11786
    Prev
    Next
    INDEX
    Explanations

    references to pharmaceutical regulatory approvals and treatments for specific medical conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MIDDLEWARE
    -0.60
    scriptId
    -0.55
    
    -0.55
    blers
    -0.53
     numberWith
    -0.53
    AsUp
    -0.52
     useAuth
    -0.52
    AnchorStyles
    -0.52
    
    -0.52
    ardo
    -0.51
    POSITIVE LOGITS
     labeling
    0.97
     labelling
    0.86
     Labeling
    0.82
     label
    0.81
     FDA
    0.80
     Food
    0.79
    Label
    0.76
    Food
    0.75
     labels
    0.74
     food
    0.72
    Activations Density 0.446%

    No Known Activations