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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 21-GEMMASCOPE-RES-16K
    6. 2869
    Prev
    Next
    INDEX
    Explanations

    conversational cues and response patterns in dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/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.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.70
    findpost
    -0.63
     فريبيس
    -0.62
    /*---
    -0.57
    gameserver
    -0.57
    }*/
    
    -0.56
    ("-");
    -0.56
     EconPapers
    -0.56
    twimg
    -0.55
     الرياضيه
    -0.55
    POSITIVE LOGITS
    Yeah
    0.88
     Yeah
    0.85
     yeah
    0.81
     exactly
    0.75
    Exactly
    0.74
     Exactly
    0.74
    Absolutely
    0.74
     absolutely
    0.71
    Totally
    0.68
    Oh
    0.68
    Activations Density 0.049%

    No Known Activations