© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 5-GEMMASCOPE-RES-16K
    11. 5670
    Prev
    Next
    INDEX
    Explanations

    references to HTTP response errors and status codes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AttributeSet
    -0.62
     Lake
    -0.54
     Affiliations
    -0.54
    isContained
    -0.52
     uParam
    -0.50
     GenerationType
    -0.50
    湖
    -0.49
    حياته
    -0.47
    dibles
    -0.46
    IMPORTED
    -0.46
    POSITIVE LOGITS
     AssemblyTitle
    0.68
     MediatR
    0.63
    illip
    0.62
    robots
    0.61
    iastes
    0.58
    UserScript
    0.58
    writeHead
    0.57
    ChildScrollView
    0.57
    ✭✭
    0.57
    GIH
    0.57
    Activations Density 0.371%

    No Known Activations