© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 2513
    Prev
    Next
    INDEX
    Explanations

    references to the term "black" and its various contexts within discussions of race

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pov
    -0.64
     Vantage
    -0.63
     müſſen
    -0.61
     AssemblyCompany
    -0.61
     Vibe
    -0.59
    omeness
    -0.59
     Puj
    -0.58
    Cyfarwyddwr
    -0.58
     Gyro
    -0.58
    vibe
    -0.57
    POSITIVE LOGITS
     Black
    1.36
    Black
    1.30
     BLACK
    1.25
     black
    1.23
    black
    1.17
    BLACK
    1.17
     zwarte
    0.85
    黑
    0.83
     Blacks
    0.82
     čier
    0.82
    Activations Density 0.082%

    No Known Activations