© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 4875
    Prev
    Next
    INDEX
    Explanations

    elements of surprise and thoughtful gestures in relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     MotionEvent
    -0.72
     estekak
    -0.71
     consultato
    -0.71
     ujednoznacz
    -0.69
    tvguidetime
    -0.67
     isNameExpr
    -0.62
     Wiktionnaire
    -0.62
    fastjson
    -0.61
     onOptions
    -0.61
    /***/
    -0.59
    POSITIVE LOGITS
     Surprise
    0.66
     surprise
    0.64
    юрпри
    0.62
    Surprise
    0.61
     surprises
    0.58
    WriteTagHelper
    0.54
     Customized
    0.54
    surprise
    0.53
    Customized
    0.48
     customized
    0.47
    Activations Density 0.152%

    No Known Activations