© 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. 6939
    Prev
    Next
    INDEX
    Explanations

    the opening token that signifies the start of a significant or highlighted section in the document

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

    Code or markup snippets

    np_acts-logits-general · gemini-2.0-flash

    code and mathematical notation

    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
    ".
    
    -0.94
    '},
    
    -0.94
     GenerationType
    -0.90
    '):
    
    -0.90
    )";
    
    -0.89
    setVerticalGroup
    -0.89
    "):
    
    -0.87
    .",
    
    -0.86
    )");
    
    -0.85
     -->>
    -0.85
    POSITIVE LOGITS
    <eos>
    1.38
    ↵
    0.82
    ↵↵
    0.79
    The
    0.78
    ↵↵↵
    0.76
    I
    0.76
    A
    0.75
    https
    0.75
    http
    0.74
    ↵↵↵↵
    0.73
    Activations Density 0.178%

    No Known Activations