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. 36-GEMMASCOPE-RES-16K
    6. 8038
    Prev
    Next
    INDEX
    Explanations

    events related to military action or conflict

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    webElementXpaths
    -0.38
     confiança
    -0.35
     Bloomfield
    -0.35
     czyn
    -0.33
     Everett
    -0.31
     åt
    -0.31
     Beaver
    -0.30
     Wege
    -0.29
     trương
    -0.28
     safety
    -0.27
    POSITIVE LOGITS
     missiles
    1.09
     missile
    1.00
     artillery
    0.97
     mortars
    0.95
     rockets
    0.89
     mortar
    0.85
     rocket
    0.84
     bombs
    0.82
     Missile
    0.81
     shells
    0.79
    Activations Density 0.249%

    No Known Activations