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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 21-GEMMASCOPE-RES-16K
    6. 510
    Prev
    Next
    INDEX
    Explanations

    conditional statements in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.97
    ValueStyle
    -0.95
     ujednoznacz
    -0.95
    ">//
    -0.92
    DockStyle
    -0.84
     ());
    -0.83
     =>
    
    -0.82
    findpost
    -0.81
     noqa
    -0.81
     $_"
    -0.80
    POSITIVE LOGITS
    (
    0.93
      
    0.69
    ((
    0.55
    =
    0.54
       
    0.52
    {
    0.51
    [
    0.48
    	
    0.47
     thier
    0.46
        
    0.44
    Activations Density 0.032%

    No Known Activations