© 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 - 65k
    9. 0-GEMMASCOPE-RES-65K
    11. 10293
    Prev
    Next
    INDEX
    Explanations

    references to tape dispensers and associated types, as well as links that begin with "https"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aspectj
    -0.67
     Janeiro
    -0.60
    styr
    -0.60
     zvuky
    -0.57
     miras
    -0.56
     Waray
    -0.56
     onAnimation
    -0.56
    Παραπομπές
    -0.56
    Искәрмәләр
    -0.55
    +:+
    -0.55
    POSITIVE LOGITS
     dispens
    0.89
     оригіналу
    0.80
     Chron
    0.79
     entrain
    0.74
     Wiz
    0.68
    Chron
    0.66
    KURZBESCHREIBUNG
    0.65
     Dispens
    0.65
    zinha
    0.63
     Enzo
    0.62
    Activations Density 0.143%

    No Known Activations