© 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. 20-GEMMASCOPE-RES-16K
    6. 7048
    Prev
    Next
    INDEX
    Explanations

    syntax elements and structure in programming code

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

    Java System class or method calls

    np_acts-logits-general · gemini-2.0-flash

    System.out.println

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <bos>
    -0.55
    self
    -0.50
     absl
    -0.50
     SDLK
    -0.49
     strlen
    -0.47
     lit
    -0.47
    jekk
    -0.47
    fwrite
    -0.46
    Self
    -0.45
     self
    -0.45
    POSITIVE LOGITS
    System
    1.06
     System
    0.94
    try
    0.78
    <>());
    0.75
    boolean
    0.69
    String
    0.66
     try
    0.65
     String
    0.64
     Syst
    0.63
     Systemic
    0.63
    Activations Density 0.178%

    No Known Activations