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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 4961
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to "Ce" as a prefix, particularly in names or terms

    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
    PreferredItem
    -0.90
    Pratique
    -0.81
    ########.
    -0.79
    ividual
    -0.78
    ніципа
    -0.77
    haway
    -0.75
    ernalia
    -0.71
    freude
    -0.71
    ništvo
    -0.70
    pran
    -0.70
    POSITIVE LOGITS
     Ce
    1.02
    Ce
    0.92
     ce
    0.90
     cer
    0.80
    ce
    0.74
    cer
    0.74
     CE
    0.74
     Cef
    0.73
     CER
    0.73
     Ceb
    0.72
    Activations Density 0.283%

    No Known Activations