© 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. 4-GEMMASCOPE-RES-16K
    11. 11487
    Prev
    Next
    INDEX
    Explanations

    issues related to emotional states and feelings of discomfort or confusion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     propOrder
    -1.02
     ſtate
    -0.79
     فريبيس
    -0.78
    parsedMessage
    -0.77
     ſta
    -0.72
    GEBURTSDATUM
    -0.72
     виправивши
    -0.71
    LabelTagHelper
    -0.70
     raiſ
    -0.70
     otomatig
    -0.69
    POSITIVE LOGITS
     become
    0.61
     get
    0.60
     becomes
    0.60
    越来越
    0.59
    LLocation
    0.57
     gets
    0.57
     became
    0.53
    Gets
    0.51
     increasingly
    0.50
     progressively
    0.48
    Activations Density 0.152%

    No Known Activations