© 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. 21-GEMMASCOPE-RES-16K
    6. 14885
    Prev
    Next
    INDEX
    Explanations

    code-related elements in programming context, particularly focusing on GTK (GIMP Toolkit) functions and structures

    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
     bcrypt
    -0.53
    '));
    
    -0.51
    '){
    
    -0.50
     graag
    -0.50
    arraycopy
    -0.49
    PMailer
    -0.49
    Rigidbody
    -0.49
    expiresIn
    -0.48
    ComponentScan
    -0.47
    ImageContext
    -0.47
    POSITIVE LOGITS
     buttons
    0.89
     display
    0.88
     UI
    0.85
     Display
    0.84
     GUI
    0.81
     button
    0.80
     gui
    0.80
     displayed
    0.80
     controls
    0.79
     selection
    0.78
    Activations Density 0.700%

    No Known Activations