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. 24-GEMMASCOPE-RES-16K
    6. 8212
    Prev
    Next
    INDEX
    Explanations

    sentences that begin with specific formatting markers or are structured in a list-like manner

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Precedes single letters like Q

    np_acts-logits-general · gemini-2.0-flash

    special characters and abbreviations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
      
    -1.53
       
    -1.27
     />";
    -1.05
          
    -1.02
    ","");
    -0.99
    !";
    -0.97
        
    -0.97
    "]));
    -0.97
           
    -0.95
     />';
    -0.95
    POSITIVE LOGITS
     ♪
    1.04
     gonna
    0.94
    ♪
    0.89
    ...
    0.82
    ս
    0.81
     Mm
    0.78
     GONNA
    0.78
    ...?
    0.70
    Mm
    0.68
     somethin
    0.68
    Activations Density 0.028%

    No Known Activations