© 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. 30-GEMMASCOPE-RES-16K
    11. 11905
    Prev
    Next
    INDEX
    Explanations

    instances of the word "blue" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "Blue" (various capitalizations)

    np_acts-logits-general · gemini-2.0-flash

    blue followed by specific nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     chegada
    -0.42
     Accesorios
    -0.40
    ţiile
    -0.38
     llavero
    -0.38
     tangga
    -0.38
    as
    -0.37
    țiile
    -0.36
    RunWith
    -0.35
    tidaknya
    -0.35
    Rptr
    -0.34
    POSITIVE LOGITS
    Blue
    1.01
     Blue
    0.99
    BLUE
    0.94
     BLU
    0.94
     BLUE
    0.91
    BLU
    0.91
    blu
    0.88
     Blu
    0.88
     blu
    0.87
    blue
    0.87
    Activations Density 0.059%

    No Known Activations