© 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. 15690
    Prev
    Next
    INDEX
    Explanations

    the word "separate" in various contexts

    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
    ècie
    -0.80
     Clint
    -0.72
    Clint
    -0.69
     ContentValues
    -0.68
     Gaston
    -0.67
     Gamb
    -0.64
     Bewegungs
    -0.64
     AssemblyProduct
    -0.63
     Ärz
    -0.62
    vänt
    -0.61
    POSITIVE LOGITS
     separate
    1.71
     seperate
    1.66
     Separate
    1.65
    separate
    1.64
    Separate
    1.60
     SEPAR
    1.53
     Separ
    1.49
     separ
    1.43
     separat
    1.41
     separates
    1.40
    Activations Density 0.070%

    No Known Activations