© 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. 7880
    Prev
    Next
    INDEX
    Explanations

    commands or instructions to perform actions

    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
     koszulka
    -0.79
     Sams
    -0.76
     AssemblyCulture
    -0.76
    dhism
    -0.74
     PMS
    -0.72
    theless
    -0.72
    PMS
    -0.72
    Cordialement
    -0.71
     immobilier
    -0.71
     cdti
    -0.71
    POSITIVE LOGITS
    take
    2.96
     take
    2.94
    Take
    2.85
     Take
    2.75
    Taking
    2.65
     TAKE
    2.63
     taking
    2.56
    taking
    2.55
     Taking
    2.54
    TAKE
    2.52
    Activations Density 0.062%

    No Known Activations