© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 9559
    Prev
    Next
    INDEX
    Explanations

    function declarations and their attributes within a code context

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

    Code or configuration file snippets

    np_acts-logits-general · gemini-2.0-flash

    code identifiers and types

    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
    ancy
    -0.57
     CURIAM
    -0.56
     Bias
    -0.50
    وبی
    -0.49
    postMessage
    -0.48
    ONTO
    -0.48
    ância
    -0.47
    jus
    -0.47
    Bias
    -0.47
    uba
    -0.46
    POSITIVE LOGITS
                
    0.90
    InjectAttribute
    0.65
    XmlAccessorType
    0.59
    oredCriteria
    0.57
    webElementGuid
    0.57
    writeFieldEnd
    0.56
     nine
    0.56
    aarrggbb
    0.56
     unknownFields
    0.56
     ninth
    0.55
    Activations Density 0.185%

    No Known Activations