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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 15-GEMMASCOPE-RES-16K
    6. 1594
    Prev
    Next
    INDEX
    Explanations

    discussions about the pros and cons of certain abilities, actions, or concepts, particularly in a critical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GraphicsUnit
    -0.98
    "):
    
    -0.97
     الاطلاع
    -0.84
    '):
    
    -0.80
     Paglinawan
    -0.76
    ")));
    
    -0.76
    )");
    
    -0.76
    mybatisplus
    -0.73
     ")");
    -0.73
    ...");
    
    -0.73
    POSITIVE LOGITS
     ours
    0.77
    今回
    0.74
    here
    0.73
     here
    0.72
    今回も
    0.70
    今回は
    0.70
    今回の
    0.68
    何况
    0.65
    更何况
    0.65
     this
    0.62
    Activations Density 0.638%

    No Known Activations