Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 9980
    Prev
    Next
    INDEX
    Explanations

    terms related to race and its implications in society

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    InjectAttribute
    -1.16
     Audiodateien
    -0.97
    SequentialGroup
    -0.92
     AssemblyCulture
    -0.91
    BibitemShut
    -0.87
    حياته
    -0.87
    //};
    -0.86
    AndEndTag
    -0.86
    ]--;
    -0.84
    PyExc
    -0.84
    POSITIVE LOGITS
     race
    0.89
     races
    0.83
     Race
    0.80
    Race
    0.74
     Races
    0.74
     RACE
    0.70
     Rac
    0.69
    car
    0.64
    course
    0.63
    race
    0.63
    Activations Density 0.074%

    No Known Activations