© 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. 9775
    Prev
    Next
    INDEX
    Explanations

    aspects related to systematic approaches and their evaluation

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

    Preceding words like "aspect," "level," "fashion," "piece," "sense," etc

    np_acts-logits-general · gemini-2.0-flash

    attributes and states

    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
    цездатний
    -0.63
     يتيمه
    -0.61
    AntiForgeryToken
    -0.60
    Iné
    -0.57
    UserScript
    -0.56
     tubercle
    -0.56
     Pingback
    -0.54
    NewLabel
    -0.54
    Rohy
    -0.54
     foncé
    -0.52
    POSITIVE LOGITS
    uality
    0.69
    yarnpkg
    0.67
    
    0.66
    SequentialGroup
    0.64
     involving
    0.62
     of
    0.55
    eradish
    0.54
     تانيه
    0.53
     whatsoever
    0.53
     thereof
    0.53
    Activations Density 1.580%

    No Known Activations