© 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. 5-GEMMASCOPE-RES-16K
    11. 514
    Prev
    Next
    INDEX
    Explanations

    references and mentions of the word "refer" 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 @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mybatisplus
    -0.84
     Double
    -0.70
     
    -0.69
     W
    -0.68
    bigoplus
    -0.68
     M
    -0.67
     E
    -0.66
    mantel
    -0.66
     Blue
    -0.65
    grenze
    -0.65
    POSITIVE LOGITS
    Refer
    1.74
     referrals
    1.73
     referred
    1.72
     refer
    1.70
     REFER
    1.66
     referral
    1.66
     Refer
    1.57
     Referral
    1.55
    refer
    1.51
    referred
    1.47
    Activations Density 0.086%

    No Known Activations