© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 13143
    Prev
    Next
    INDEX
    Explanations

    numerical values and related coding structures

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

    Hexadecimal code or memory addresses

    np_acts-logits-general · gemini-2.0-flash

    mathematical notation and code snippets

    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
    "]);
    
    -0.95
    '],
    
    -0.94
    "],
    
    -0.93
    ']);
    
    -0.92
    "])
    
    -0.92
    "]];
    -0.90
    ()");
    -0.86
    ']],
    -0.85
    stdc
    -0.83
    "),
    
    -0.83
    POSITIVE LOGITS
    ValueStyle
    0.46
     runt
    0.45
    HCR
    0.42
    ²
    0.42
     osa
    0.42
     pinulongan
    0.42
    routeProvider
    0.40
    ControllerAdvice
    0.40
    2
    0.40
    Mc
    0.39
    Activations Density 1.082%

    No Known Activations