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. 15-GEMMASCOPE-RES-16K
    6. 8766
    Prev
    Next
    INDEX
    Explanations

    the presence of structured data or programming constructs like objects and arrays

    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
     незавершена
    -0.62
     للمعارف
    -0.60
    Читати
    -0.59
     xanth
    -0.56
     EdgeInsets
    -0.56
    éphane
    -0.54
     муніципалі
    -0.54
     abzu
    -0.53
    Charsets
    -0.53
     gyn
    -0.52
    POSITIVE LOGITS
    ↵
    1.35
    __':
    
    1.13
    __":
    
    1.08
    ↵↵
    1.02
    ]),
    
    0.97
     };
    
    0.96
     ***!
    0.95
    ']){
    0.91
    }();
    0.91
    )=>{
    
    0.90
    Activations Density 0.100%

    No Known Activations