© 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 - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 17140
    Prev
    Next
    INDEX
    Explanations

    commands or actions related to processing and generating content in a functional context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     surla
    -0.88
    principalTable
    -0.80
     Efq
    -0.76
    sizeCache
    -0.76
    DebuggerNonUser
    -0.73
     Jefus
    -0.72
     Theſe
    -0.71
    "},
    
    -0.70
    الحياه
    -0.69
    ."],
    -0.69
    POSITIVE LOGITS
     then
    0.66
     assim
    0.54
     thereby
    0.50
    fetchall
    0.50
    then
    0.49
     them
    0.48
    ster
    0.47
     transforme
    0.47
     thus
    0.46
    Портал
    0.46
    Activations Density 0.130%

    No Known Activations