© 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. 14213
    Prev
    Next
    INDEX
    Explanations

    function calls related to data retrieval or manipulation

    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
     Trotter
    -0.73
     saites
    -0.72
    IVEREF
    -0.71
    '}>
    -0.71
    bhan
    -0.69
     Tia
    -0.68
     Trento
    -0.66
     Luz
    -0.66
    '));
    
    -0.65
     ligiloj
    -0.64
    POSITIVE LOGITS
    Get
    1.60
     Get
    1.22
    GET
    0.86
     GetAll
    0.86
    GetName
    0.80
     GetData
    0.79
     testGet
    0.77
     GET
    0.74
    GetAll
    0.72
    GetItem
    0.70
    Activations Density 0.115%

    No Known Activations