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. 11-GEMMASCOPE-RES-16K
    6. 1906
    Prev
    Next
    INDEX
    Explanations

    phrases related to moral values and ethical considerations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ########.
    -0.84
    Попис
    -0.77
     navideños
    -0.70
     ModelRenderer
    -0.69
    TextAppearance
    -0.68
     calendriers
    -0.67
    featureID
    -0.65
     évi
    -0.65
     Bennett
    -0.65
    دانشنامهٔ
    -0.64
    POSITIVE LOGITS
            
    0.93
    <tr>
    0.86
        
    0.83
           
    0.81
       
    0.81
    </th>
    0.80
    		
    0.79
    enumi
    0.78
    </h2>
    0.77
         
    0.77
    Activations Density 0.039%

    No Known Activations