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. 3-GEMMASCOPE-RES-16K
    6. 9750
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ter
    -0.57
     
    -0.54
     my
    -0.53
     Har
    -0.49
      
    -0.48
     ada
    -0.48
    Driven
    -0.48
     Ter
    -0.47
     Re
    -0.46
    awan
    -0.46
    POSITIVE LOGITS
    ########.
    0.85
    tagext
    0.84
     ExecuteAsync
    0.81
    reactstrap
    0.80
     newOwner
    0.80
     ویکی‌پدیای
    0.79
    MethodManager
    0.79
    NameInMap
    0.79
     GenerationType
    0.78
    
    0.78
    Activations Density 1.442%

    No Known Activations