© 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. 21-GEMMASCOPE-RES-16K
    11. 12799
    Prev
    Next
    INDEX
    Explanations

    phrases expressing gratitude and recommendations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zarchiwizowane
    -0.66
    Lähteet
    -0.64
     Interesting
    -0.60
    Interesting
    -0.59
     interest
    -0.59
    Iné
    -0.56
    ValueStyle
    -0.56
     derog
    -0.54
     interesting
    -0.54
    Interess
    -0.54
    POSITIVE LOGITS
     couldn
    0.82
     truly
    0.80
     hâte
    0.73
    truly
    0.72
     verkligen
    0.69
    couldn
    0.67
    Truly
    0.66
     Truly
    0.66
    本当
    0.65
     litté
    0.65
    Activations Density 0.160%

    No Known Activations