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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 8447
    Prev
    Next
    INDEX
    Explanations

    references to injuries and trauma

    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
    Portail
    -0.61
    ⓧ
    -0.55
     oprot
    -0.54
     المعيارى
    -0.54
    stdc
    -0.54
     Democrá
    -0.52
     становника
    -0.51
    Portale
    -0.50
    tagext
    -0.49
     jsPsych
    -0.49
    POSITIVE LOGITS
     injury
    3.41
     Injury
    3.16
     injuries
    2.97
    injury
    2.95
    Injury
    2.94
     Injuries
    2.78
     injured
    2.70
     injure
    2.64
    Injuries
    2.61
     INJ
    2.53
    Activations Density 0.149%

    No Known Activations