© 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. 4-GEMMASCOPE-RES-16K
    11. 15704
    Prev
    Next
    INDEX
    Explanations

    the concept of "proper" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Catar
    -0.80
    ReusableCell
    -0.78
    AddField
    -0.78
    chenkt
    -0.77
     Ringo
    -0.77
     iCloud
    -0.77
    chossen
    -0.76
    numerusform
    -0.75
     ContentValues
    -0.75
     SqlCommand
    -0.75
    POSITIVE LOGITS
     proper
    2.31
     Proper
    2.27
    Proper
    2.25
     PROPER
    2.10
    proper
    2.08
     properly
    2.02
    properly
    1.84
     Properly
    1.81
     improper
    1.32
     Improper
    1.30
    Activations Density 0.098%

    No Known Activations