© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 35425
    Prev
    Next
    INDEX
    Explanations

    terms related to escalation or increases in intensity or scope

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

    escalation and relapse

    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
    uchi
    -0.47
     Virginie
    -0.44
    msgTypes
    -0.43
    VIAF
    -0.42
    postdata
    -0.42
    listbox
    -0.42
    viewDidLoad
    -0.42
    byt
    -0.41
    DTD
    -0.40
     checkBox
    -0.40
    POSITIVE LOGITS
     escalation
    1.84
     escalate
    1.75
    escal
    1.73
     Escal
    1.68
    Escal
    1.67
     escalated
    1.61
     escal
    1.55
     escalating
    1.45
     escalada
    1.12
     escala
    0.93
    Activations Density 0.003%

    No Known Activations