© 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. 1-GEMMASCOPE-RES-16K
    6. 10865
    Prev
    Next
    INDEX
    Explanations

    pronouns and their usage in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ValueStyle
    -1.05
    endphp
    -0.90
    出版年
    -0.87
    setVerticalGroup
    -0.78
     Мексичка
    -0.76
     onCreateView
    -0.74
    URLException
    -0.73
     MainAxisSize
    -0.69
    moduleId
    -0.66
    
    -0.65
    POSITIVE LOGITS
     called
    0.64
     Called
    0.63
    Called
    0.60
     CALLED
    0.60
    called
    0.55
     называется
    0.49
     chiamato
    0.49
    dataTables
    0.49
    Call
    0.48
     bune
    0.48
    Activations Density 0.212%

    No Known Activations