© 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-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 106168
    Prev
    Next
    INDEX
    Explanations

    numerical values associated with scientific publications or references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Lähteet
    -0.66
     propOrder
    -0.60
     bezeichneter
    -0.52
     gepubliceerd
    -0.50
    ellemző
    -0.49
     ujednoznacz
    -0.49
    ticals
    -0.47
    :+:
    -0.47
     ostavi
    -0.47
     hroz
    -0.47
    POSITIVE LOGITS
    __(/*!
    0.41
    brigens
    0.36
    principalTable
    0.35
    authority
    0.33
     authority
    0.33
    VYMaps
    0.33
     general
    0.32
    OrNil
    0.32
    setOnItem
    0.32
    Portail
    0.32
    Activations Density 0.012%

    No Known Activations