© 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-2-9B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 13055
    Prev
    Next
    INDEX
    Explanations

    references to moral justifications for actions and the consequences of those actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ProtoMessage
    -0.73
    CppMethod
    -0.72
     informée
    -0.72
     utafitiHapana
    -0.70
     sumpay
    -0.68
    adaptiveStyles
    -0.68
    MessageOf
    -0.67
     EconPapers
    -0.67
    Tikang
    -0.66
    httphttps
    -0.65
    POSITIVE LOGITS
    明明
    0.34
     sobretudo
    0.34
     inevitably
    0.33
    InputTagHelper
    0.32
     vectorielle
    0.32
     når
    0.30
     mennesker
    0.30
    topRight
    0.30
     humaine
    0.30
     éprou
    0.30
    Activations Density 3.482%

    No Known Activations