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. 19-GEMMASCOPE-RES-16K
    6. 614
    Prev
    Next
    INDEX
    Explanations

    references to food and dining experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    一把
    -0.53
     lĩnh
    -0.52
    inqu
    -0.50
     foramen
    -0.46
    innoc
    -0.46
    rung
    -0.46
    tach
    -0.46
     akar
    -0.46
    paramMap
    -0.45
    øk
    -0.45
    POSITIVE LOGITS
     buffet
    1.38
    buffet
    1.10
     Buffet
    1.07
     catered
    0.84
     Buffett
    0.80
     served
    0.79
    뷔
    0.76
     BUFF
    0.74
    Buff
    0.72
     buff
    0.72
    Activations Density 0.095%

    No Known Activations