© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 9628
    Prev
    Next
    INDEX
    Explanations

    variations or distinctions between items or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ]>=
    -0.55
    jsonwebtoken
    -0.52
    JKLM
    -0.52
    totic
    -0.50
    PARSER
    -0.49
     başına
    -0.47
    melis
    -0.47
    học
    -0.47
     góry
    -0.46
     stable
    -0.46
    POSITIVE LOGITS
     difference
    1.92
     differences
    1.87
     Differences
    1.79
    difference
    1.78
     Difference
    1.76
    Differences
    1.73
    Difference
    1.72
     DIFFERENCE
    1.70
    differences
    1.66
     Differ
    1.62
    Activations Density 0.411%

    No Known Activations