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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 4805
    Prev
    Next
    INDEX
    Explanations

    specific dishes and ingredients related to various cuisines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RegressionTest
    -0.75
     فريبيس
    -0.72
    Vidite
    -0.66
    erom
    -0.62
     Bubble
    -0.62
     Rota
    -0.61
     Tuchel
    -0.60
    Portail
    -0.58
    tinyos
    -0.58
     HasFactory
    -0.57
    POSITIVE LOGITS
     meat
    1.13
     beef
    0.97
    meat
    0.96
    beef
    0.90
    fleisch
    0.88
     pork
    0.87
     steak
    0.87
    Beef
    0.87
     meats
    0.86
     Beef
    0.85
    Activations Density 0.124%

    No Known Activations