© 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-2-9B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 5805
    Prev
    Next
    INDEX
    Explanations

    discussions centered around practical applications or implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 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
    Batch
    -0.72
     Batch
    -0.71
    batch
    -0.69
     batch
    -0.68
    BATCH
    -0.65
     BATCH
    -0.61
    ArrowToggle
    -0.60
     Савезне
    -0.59
     pageContext
    -0.57
    fjspx
    -0.55
    POSITIVE LOGITS
     practical
    1.64
    practical
    1.52
     Practical
    1.50
    Practical
    1.46
     PRACTICAL
    1.37
     practicality
    1.04
     praktische
    0.99
     prof
    0.94
     praktischen
    0.93
    PRACT
    0.91
    Activations Density 0.043%

    No Known Activations