© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 1322
    Prev
    Next
    INDEX
    Explanations

    references to "parties" involved in agreements or legal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ########.
    -0.59
     之
    -0.55
     dokun
    -0.51
    annica
    -0.50
     ambassadors
    -0.50
     Image
    -0.49
    gdx
    -0.49
    seed
    -0.49
     Shee
    -0.49
     tricks
    -0.49
    POSITIVE LOGITS
     parties
    0.94
    Parties
    0.85
     PARTIES
    0.83
     expire
    0.82
    parties
    0.79
     Parties
    0.79
     StatefulWidget
    0.78
    __":
    
    0.77
     expires
    0.77
     perfons
    0.76
    Activations Density 0.030%

    No Known Activations