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-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 69325
    Prev
    Next
    INDEX
    Explanations

    references to historical geopolitical conflicts and diplomatic tensions

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

    escalation and crisis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    httphttps
    -0.50
    ########.
    -0.49
    (!__
    -0.47
    RetentionPolicy
    -0.43
    ModelSerializer
    -0.42
    TextWatcher
    -0.42
    ViewImports
    -0.42
     jsPsych
    -0.40
    WillAppear
    -0.39
    Referencies
    -0.39
    POSITIVE LOGITS
     escalation
    1.27
    escal
    1.11
     escalate
    1.09
     escalada
    1.05
    Escal
    1.03
     escal
    1.01
     escalating
    0.97
     Escal
    0.96
     escalated
    0.95
     tensions
    0.91
    Activations Density 0.063%

    No Known Activations