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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 6-GEMMASCOPE-RES-16K
    6. 13174
    Prev
    Next
    INDEX
    Explanations

    instances of the word "proper" or similar variations indicating standards or qualifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onnaissance
    -0.93
     ContentValues
    -0.90
    InjectAttribute
    -0.89
    RetentionPolicy
    -0.87
     GenerationType
    -0.85
    omitempty
    -0.83
     tourmaline
    -0.83
    UserScript
    -0.82
    HasMaxLength
    -0.81
    chenkt
    -0.81
    POSITIVE LOGITS
     Proper
    1.73
    Proper
    1.72
     PROPER
    1.67
     proper
    1.67
     properly
    1.56
    proper
    1.48
     Properly
    1.46
    properly
    1.41
     Improper
    1.04
     improper
    1.04
    Activations Density 0.080%

    No Known Activations