© 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 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. 8282
    Prev
    Next
    INDEX
    Explanations

    references to the name "Adam" and specific terms related to coding and technical language

    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
     pinulongan
    -0.81
    stdc
    -0.76
     propOrder
    -0.75
    Descripció
    -0.72
     kaarangay
    -0.71
    principalTable
    -0.71
     perfons
    -0.68
    ioutil
    -0.67
     Sigism
    -0.66
     الرياضيه
    -0.66
    POSITIVE LOGITS
     Kyle
    0.74
     Tom
    0.71
     horizon
    0.64
     Adam
    0.64
     Dan
    0.62
    Syntax
    0.62
    Kyle
    0.60
    horizon
    0.57
    Tom
    0.53
     Thiel
    0.53
    Activations Density 0.027%

    No Known Activations