© 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. 3554
    Prev
    Next
    INDEX
    Explanations

    sections of code or structured data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     AssemblyCulture
    -0.73
    CloseOperation
    -0.73
     ProtoMessage
    -0.70
    antMatchers
    -0.66
    Hentet
    -0.65
    httphttps
    -0.64
    اریخ
    -0.63
    mybatisplus
    -0.63
     distanciation
    -0.61
     GenerationType
    -0.61
    POSITIVE LOGITS
    principalTable
    0.52
    ymus
    0.47
     متعلقه
    0.44
    geç
    0.43
    WriteAttribute
    0.43
     luận
    0.42
    MathML
    0.42
    Pranala
    0.41
     nguyên
    0.41
    Pré
    0.40
    Activations Density 0.022%

    No Known Activations