© 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. 2-GEMMASCOPE-RES-16K
    6. 7151
    Prev
    Next
    INDEX
    Explanations

    instances of non-lexical tokens or punctuations, possibly indicating special formatting or metadata

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCulture
    -0.77
     dysplasia
    -0.66
     виправивши
    -0.63
    Rowan
    -0.63
     syner
    -0.63
     Lons
    -0.62
     Barna
    -0.62
    Weather
    -0.62
    unhofer
    -0.62
     Chwiliwch
    -0.61
    POSITIVE LOGITS
    ControllerAdvice
    0.79
     BorderRadius
    0.77
     itſelf
    0.76
     Theſe
    0.72
     payé
    0.70
    WriteHeader
    0.70
     LXXX
    0.70
     iſt
    0.69
     
    0.69
    acios
    0.69
    Activations Density 0.187%

    No Known Activations