© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 14615
    Prev
    Next
    INDEX
    Explanations

    the word "ce"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     maternelle
    -0.68
     materna
    -0.68
     huom
    -0.62
     îna
    -0.61
     Delegate
    -0.61
    quierda
    -0.60
     esterna
    -0.56
     traccia
    -0.56
     Lumb
    -0.56
     UserRepository
    -0.55
    POSITIVE LOGITS
     ce
    1.25
     Ce
    0.94
     lifetime
    0.86
    Ce
    0.83
     vo
    0.78
     Lifetime
    0.78
    anthin
    0.74
     Vo
    0.73
    Lifetime
    0.70
    Marshaller
    0.70
    Activations Density 0.075%

    No Known Activations