© 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. 2-GEMMASCOPE-RES-16K
    11. 8661
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize speaking or communicating with someone

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    最快更新
    -0.71
     Putih
    -0.66
     оригіналу
    -0.62
    ngdoc
    -0.61
    popularity
    -0.58
     Arhi
    -0.56
    
    -0.55
    Халык
    -0.55
    Matchers
    -0.54
     FormsModule
    -0.54
    POSITIVE LOGITS
     conversation
    0.85
     tell
    0.71
     talk
    0.71
     conversations
    0.69
    conversation
    0.68
     conversación
    0.67
     Conversation
    0.65
     Gespräch
    0.65
     CONVERS
    0.64
    conversations
    0.63
    Activations Density 0.129%

    No Known Activations