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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 15-GEMMASCOPE-RES-16K
    6. 2871
    Prev
    Next
    INDEX
    Explanations

    references to beliefs, race, and the idea of superiority or inferiority among human beings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 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
     (‘
    -0.49
     (“
    -0.40
     (=
    -0.40
    abbix
    -0.40
    didReceive
    -0.39
    .’”
    -0.38
    、『
    -0.37
     Kras
    -0.37
     («
    -0.37
    Ú
    -0.37
    POSITIVE LOGITS
     linkovi
    0.86
    EndInit
    0.80
     hence
    0.80
     pinulongan
    0.78
     AssemblyCulture
    0.77
     للاسماء
    0.75
    SharedCtor
    0.75
    BeginInit
    0.74
     مشين
    0.74
     They
    0.71
    Activations Density 0.353%

    No Known Activations