© 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. 22-GEMMASCOPE-RES-16K
    6. 3994
    Prev
    Next
    INDEX
    Explanations

    instances of significant numeric values or identifiers

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

    Code imports/includes and related symbols

    np_acts-logits-general · gemini-2.0-flash

    code termination

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    =$?
    -1.06
    >\<^
    -1.02
    NUMX
    -1.01
     $_"
    -0.96
    \<^
    -0.95
    ^(@)
    -0.94
    )";
    
    -0.91
     -->>
    -0.90
    ,‎
    -0.89
    — 
    -0.89
    POSITIVE LOGITS
    ↵
    1.07
    ↵↵
    1.06
    <eos>
    1.05
    import
    0.98
     import
    0.79
    ↵↵↵
    0.77
    class
    0.76
    export
    0.72
    ↵↵↵↵
    0.70
    @
    0.67
    Activations Density 0.111%

    No Known Activations