© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 5522
    Prev
    Next
    INDEX
    Explanations

    terms related to comprehension and insight

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 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
    
    -0.50
    nomin
    -0.48
     auroit
    -0.47
    mobileqq
    -0.46
     feroit
    -0.46
    zarchiwizowane
    -0.44
     pouvoit
    -0.44
     vaisselle
    -0.43
    adverti
    -0.42
     Crows
    -0.42
    POSITIVE LOGITS
     understanding
    1.76
     understand
    1.69
     Understanding
    1.65
    Understanding
    1.59
    understanding
    1.57
     Understand
    1.54
     understands
    1.52
    understand
    1.51
    Understand
    1.48
     understood
    1.41
    Activations Density 0.132%

    No Known Activations