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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 3490
    Prev
    Next
    INDEX
    Explanations

    terms relating to legal conditions and licensing agreements

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

    technical programming and mathematical content

    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
    LookAnd
    -0.69
    省市镇
    -0.66
    mybatisplus
    -0.61
    amentals
    -0.59
    tagHelperRunner
    -0.58
    MENAFN
    -0.57
    pias
    -0.56
    richTextPanel
    -0.55
     Aes
    -0.54
    grine
    -0.54
    POSITIVE LOGITS
    dukan
    0.51
    TintMode
    0.50
     Isol
    0.48
     gomma
    0.46
     européennes
    0.46
     détach
    0.45
    Hons
    0.44
    gemene
    0.44
     JButton
    0.43
     totalCount
    0.42
    Activations Density 0.052%

    No Known Activations