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. 10-GEMMASCOPE-RES-16K
    6. 15980
    Prev
    Next
    INDEX
    Explanations

    phrases related to acceptance and understanding in relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :",
    -0.79
    _"+
    -0.74
    )");
    
    -0.73
    よいよ
    -0.72
    "));
    
    -0.72
     "");
    
    -0.71
    :");
    
    -0.71
    "]:
    -0.71
    {}",
    -0.71
    )):
    
    -0.71
    POSITIVE LOGITS
     aswell
    0.94
     nahilalakip
    0.82
    mybatisplus
    0.78
     مرئيه
    0.73
    Personendaten
    0.73
     Aussi
    0.73
    väl
    0.70
     تضيفلها
    0.69
     CreateTagHelper
    0.67
    yntaxException
    0.67
    Activations Density 0.064%

    No Known Activations