© 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. 5164
    Prev
    Next
    INDEX
    Explanations

    elements related to data structure definitions and attributes

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

    "Dat" or "datatype" after certain symbols

    np_acts-logits-general · gemini-2.0-flash

    data and datatype identifiers

    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
    styleType
    -0.64
    veur
    -0.62
     ACE
    -0.61
     Arn
    -0.61
     Sule
    -0.61
     Victor
    -0.60
     Vick
    -0.60
    CppMethod
    -0.59
     Sultan
    -0.58
     Boro
    -0.58
    POSITIVE LOGITS
     Dat
    1.80
    Dat
    1.67
     DAT
    1.64
    DAT
    1.52
     dat
    1.51
     dataset
    1.42
    dat
    1.38
     Dataset
    1.32
    dataset
    1.22
    Dataset
    1.22
    Activations Density 0.213%

    No Known Activations