© 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. 3-GEMMASCOPE-RES-16K
    6. 667
    Prev
    Next
    INDEX
    Explanations

    the presence of parentheses and different bracket-related syntax elements in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ValueStyle
    -0.65
     @}
    -0.60
    minas
    -0.58
    WindowConstants
    -0.57
     Fid
    -0.56
     yol
    -0.55
    ATHAN
    -0.55
    ATRO
    -0.55
     tuyến
    -0.55
    ằ
    -0.54
    POSITIVE LOGITS
    __':
    
    1.06
    __':
    0.91
    __":
    
    0.85
    '])){
    0.83
    ']))
    
    0.81
     ReactDOM
    0.79
    ))){
    0.75
    ++){
    
    0.73
    ++)
    
    0.73
    __":
    0.72
    Activations Density 0.103%

    No Known Activations