© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 9753
    Prev
    Next
    INDEX
    Explanations

    color-related terms, particularly those associated with shades of green and red

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     prestaciones
    -0.57
     AssemblyCompany
    -0.53
    LookAnd
    -0.51
    gdx
    -0.49
    lamento
    -0.47
    atorship
    -0.47
     wijze
    -0.47
     pouvoit
    -0.47
    quiao
    -0.46
    maßen
    -0.46
    POSITIVE LOGITS
     Blue
    0.86
     Red
    0.84
     blue
    0.84
    Blue
    0.79
     Yellow
    0.78
     Green
    0.77
     red
    0.76
     BLUE
    0.76
    Red
    0.75
    Yellow
    0.74
    Activations Density 0.297%

    No Known Activations