© 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. 24-GEMMASCOPE-RES-16K
    6. 16100
    Prev
    Next
    INDEX
    Explanations

    codes and structures related to programming configurations

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

    Values assigned to keys

    np_acts-logits-general · gemini-2.0-flash

    boolean true or undefined followed by comma

    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
     "")
    
    -1.10
    )";
    
    -1.07
    ')
    
    -1.04
    ";
    
    -1.03
    )");
    
    -1.02
     []
    
    -1.00
    ")
    
    -1.00
     "");
    
    -0.98
    }")
    
    -0.97
    .";
    
    -0.96
    POSITIVE LOGITS
    ,//
    0.95
     CreateTagHelper
    0.67
     kasarigan
    0.66
    ,  
    0.65
    ,#
    0.64
     محفوظة
    0.61
    archiviato
    0.61
     noDo
    0.60
    ppins
    0.60
     exciter
    0.60
    Activations Density 0.198%

    No Known Activations