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. 10-GEMMASCOPE-RES-16K
    6. 16170
    Prev
    Next
    INDEX
    Explanations

    research related to genetic studies and antibiotic resistance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Geplaatst
    -1.04
    Personensuche
    -0.91
    Autoritní
    -0.80
    цездатний
    -0.80
     EnglishChoose
    -0.78
     насељу
    -0.78
    tagHelperRunner
    -0.74
    хьтан
    -0.73
    tvguidetime
    -0.72
     Vikipedi
    -0.72
    POSITIVE LOGITS
    didReceive
    0.74
     itſelf
    0.53
    Trusted
    0.52
    ioo
    0.50
    URG
    0.49
    ⁠
    0.49
     {},
    
    0.49
    ₂)
    0.49
    ̵
    0.48
    --)
    
    0.48
    Activations Density 0.552%

    No Known Activations