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-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 51229
    Prev
    Next
    INDEX
    Explanations

    references to the concept of war

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    words starting with war

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ecco
    -0.54
    ses
    -0.51
    esi
    -0.50
    inine
    -0.50
    onde
    -0.49
    isini
    -0.49
     Juliette
    -0.48
    onix
    -0.48
     Mimi
    -0.48
    toli
    -0.47
    POSITIVE LOGITS
     War
    2.03
    War
    1.84
     war
    1.84
     WAR
    1.57
    war
    1.44
    WAR
    1.26
     guerra
    1.20
     Wars
    1.18
     guerre
    1.13
     wars
    1.13
    Activations Density 0.014%

    No Known Activations