© 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. 15-GEMMASCOPE-RES-16K
    11. 4877
    Prev
    Next
    INDEX
    Explanations

    sentences or phrases that emphasize significant amounts of data or detail

    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
    WebServlet
    -0.88
    ly
    -0.87
    FXML
    -0.85
    formKey
    -0.83
     POM
    -0.82
     Kett
    -0.81
    gdx
    -0.79
    MethodManager
    -0.77
    atimes
    -0.76
     Bote
    -0.75
    POSITIVE LOGITS
       
    1.38
    קישורים
    1.01
         
    0.90
    0.90
        
    0.85
           
    0.83
             
    0.81
                               
    0.78
                       
    0.78
    ↵↵↵↵
    0.77
    Activations Density 0.114%

    No Known Activations