Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 8598
    Prev
    Next
    INDEX
    Explanations

    units of measurement, particularly those related to volume and concentration

    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
     prevailed
    -0.50
     ✭✭
    -0.48
     utafitiHapana
    -0.47
    
    -0.40
     prevalent
    -0.39
     extensively
    -0.38
    UserScript
    -0.38
     Prueba
    -0.38
    ้าง
    -0.37
     prevalence
    -0.37
    POSITIVE LOGITS
    ml
    1.07
     ML
    0.97
     ml
    0.95
    ML
    0.84
     shed
    0.65
     shedding
    0.60
    xml
    0.59
     sheds
    0.59
    mls
    0.59
    mlx
    0.57
    Activations Density 0.061%

    No Known Activations