© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 11768
    Prev
    Next
    INDEX
    Explanations

    specific programming elements and parameters in code snippets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    )");
    
    -1.21
    )";
    
    -1.11
    ()))
    
    -1.10
    !")
    
    -1.07
    >();
    
    -1.06
    '))
    
    -1.05
    ()));
    
    -1.04
    ")));
    
    -1.03
    >");
    
    -1.02
    !");
    
    -1.02
    POSITIVE LOGITS
     propOrder
    0.75
     CreateTagHelper
    0.66
     محفوظة
    0.66
    Espèce
    0.63
    tvguidetime
    0.62
     noDo
    0.61
     متعلقه
    0.60
    AndEndTag
    0.60
     Wallflower
    0.59
    ঠ
    0.59
    Activations Density 0.259%

    No Known Activations