© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 16059
    Prev
    Next
    INDEX
    Explanations

    words that express a positive sentiment or quality

    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
     myſelf
    -0.78
     defences
    -0.76
    InitVars
    -0.75
     aback
    -0.74
    inflater
    -0.74
     Ostat
    -0.70
    liesslich
    -0.70
     Thine
    -0.70
     loisirs
    -0.69
     tyres
    -0.68
    POSITIVE LOGITS
     wonderful
    1.76
     Wonderful
    1.67
    wonderful
    1.64
    Wonderful
    1.62
     marvelous
    1.22
     WONDER
    1.19
     wondrous
    1.16
     wonderfully
    1.10
     merveilleux
    1.07
     maravilloso
    1.03
    Activations Density 0.055%

    No Known Activations