© 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. 9477
    Prev
    Next
    INDEX
    Explanations

    mentions of defects or defective items

    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
    esez
    -0.85
    SizeF
    -0.85
    хьтан
    -0.82
    ContentAsync
    -0.81
    Décès
    -0.76
     kasarigan
    -0.70
    jspx
    -0.69
    脚注の使い方
    -0.66
    sizeCache
    -0.66
    AndEndTag
    -0.65
    POSITIVE LOGITS
     problem
    1.20
     problems
    1.15
    Problem
    1.13
     problemi
    1.10
    problem
    1.09
     problemas
    1.08
     Problem
    1.07
     problema
    1.07
     problèmes
    1.06
     problème
    1.03
    Activations Density 0.094%

    No Known Activations