© 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. 20-GEMMASCOPE-RES-65K
    11. 1970
    Prev
    Next
    INDEX
    Explanations

    technical terms and code-related elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    code and programming concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     Савезне
    -0.96
     صوتيه
    -0.91
    الإنجليزية
    -0.88
    хьтан
    -0.86
     autorytatywna
    -0.86
    saraba
    -0.85
    SequentialGroup
    -0.83
    EndProject
    -0.81
     ModelExpression
    -0.81
    Portail
    -0.78
    POSITIVE LOGITS
     lutte
    0.49
     couvert
    0.44
    lahir
    0.42
     gekomen
    0.40
     narrativa
    0.40
    旗
    0.39
     vermelhas
    0.39
     state
    0.39
     AttributeSet
    0.39
    ICE
    0.38
    Activations Density 0.067%

    No Known Activations