© 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. 2-GEMMASCOPE-RES-16K
    11. 2838
    Prev
    Next
    INDEX
    Explanations

    the repeated presence of the word "Blue."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AnchorTagHelper
    -0.43
    ensement
    -0.40
     utafitiHapana
    -0.40
    发表于
    -0.40
    PreExecute
    -0.40
    IndentedString
    -0.39
    Xna
    -0.38
    anches
    -0.36
    Portale
    -0.36
     onBind
    -0.36
    POSITIVE LOGITS
    Blue
    0.78
    blue
    0.75
     Blue
    0.73
     BLUE
    0.73
    BLUE
    0.68
     blue
    0.66
     published
    0.58
    TestingModule
    0.57
     Blueberry
    0.55
     PUBLISHED
    0.54
    Activations Density 0.152%

    No Known Activations